diff options
Diffstat (limited to 'tools')
26 files changed, 675 insertions, 96 deletions
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index 66f04a4846a5..43fdbbfe41bb 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -363,7 +363,9 @@ static int do_show(int argc, char **argv) if (fd < 0) return -1; - return show_prog(fd); + err = show_prog(fd); + close(fd); + return err; } if (argc) diff --git a/tools/power/x86/turbostat/Makefile b/tools/power/x86/turbostat/Makefile index 045f5f7d68ab..13f1e8b9ac52 100644 --- a/tools/power/x86/turbostat/Makefile +++ b/tools/power/x86/turbostat/Makefile @@ -9,9 +9,10 @@ ifeq ("$(origin O)", "command line") endif turbostat : turbostat.c -override CFLAGS += -Wall -I../../../include +override CFLAGS += -O2 -Wall -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' override CFLAGS += -DINTEL_FAMILY_HEADER='"../../../../arch/x86/include/asm/intel-family.h"' +override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 75fc4fb9901c..b2a86438f074 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -39,7 +39,6 @@ FILE *outf; int *fd_percpu; struct timeval interval_tv = {5, 0}; struct timespec interval_ts = {5, 0}; -struct timespec one_msec = {0, 1000000}; unsigned int num_iterations; unsigned int debug; unsigned int quiet; @@ -60,6 +59,7 @@ unsigned int do_irtl_hsw; unsigned int units = 1000000; /* MHz etc */ unsigned int genuine_intel; unsigned int authentic_amd; +unsigned int hygon_genuine; unsigned int max_level, max_extended_level; unsigned int has_invariant_tsc; unsigned int do_nhm_platform_info; @@ -100,6 +100,7 @@ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ unsigned int has_misc_feature_control; unsigned int first_counter_read = 1; +int ignore_stdin; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -166,6 +167,7 @@ size_t cpu_present_setsize, cpu_affinity_setsize, cpu_subset_size; struct thread_data { struct timeval tv_begin; struct timeval tv_end; + struct timeval tv_delta; unsigned long long tsc; unsigned long long aperf; unsigned long long mperf; @@ -506,6 +508,7 @@ unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAU unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; #define DO_BIC(COUNTER_NAME) (bic_enabled & bic_present & COUNTER_NAME) +#define DO_BIC_READ(COUNTER_NAME) (bic_present & COUNTER_NAME) #define ENABLE_BIC(COUNTER_NAME) (bic_enabled |= COUNTER_NAME) #define BIC_PRESENT(COUNTER_BIT) (bic_present |= COUNTER_BIT) #define BIC_NOT_PRESENT(COUNTER_BIT) (bic_present &= ~COUNTER_BIT) @@ -849,7 +852,6 @@ int dump_counters(struct thread_data *t, struct core_data *c, outp += sprintf(outp, "pc8: %016llX\n", p->pc8); outp += sprintf(outp, "pc9: %016llX\n", p->pc9); outp += sprintf(outp, "pc10: %016llX\n", p->pc10); - outp += sprintf(outp, "pc10: %016llX\n", p->pc10); outp += sprintf(outp, "cpu_lpi: %016llX\n", p->cpu_lpi); outp += sprintf(outp, "sys_lpi: %016llX\n", p->sys_lpi); outp += sprintf(outp, "Joules PKG: %0X\n", p->energy_pkg); @@ -911,7 +913,7 @@ int format_counters(struct thread_data *t, struct core_data *c, if (DO_BIC(BIC_TOD)) outp += sprintf(outp, "%10ld.%06ld\t", t->tv_end.tv_sec, t->tv_end.tv_usec); - interval_float = tv_delta.tv_sec + tv_delta.tv_usec/1000000.0; + interval_float = t->tv_delta.tv_sec + t->tv_delta.tv_usec/1000000.0; tsc = t->tsc * tsc_tweak; @@ -1287,6 +1289,14 @@ delta_core(struct core_data *new, struct core_data *old) } } +int soft_c1_residency_display(int bic) +{ + if (!DO_BIC(BIC_CPU_c1) || use_c1_residency_msr) + return 0; + + return DO_BIC_READ(bic); +} + /* * old = new - old */ @@ -1309,6 +1319,7 @@ delta_thread(struct thread_data *new, struct thread_data *old, * over-write old w/ new so we can print end of interval values */ + timersub(&new->tv_begin, &old->tv_begin, &old->tv_delta); old->tv_begin = new->tv_begin; old->tv_end = new->tv_end; @@ -1322,7 +1333,8 @@ delta_thread(struct thread_data *new, struct thread_data *old, old->c1 = new->c1 - old->c1; - if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || + soft_c1_residency_display(BIC_Avg_MHz)) { if ((new->aperf > old->aperf) && (new->mperf > old->mperf)) { old->aperf = new->aperf - old->aperf; old->mperf = new->mperf - old->mperf; @@ -1404,6 +1416,8 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data t->tv_begin.tv_usec = 0; t->tv_end.tv_sec = 0; t->tv_end.tv_usec = 0; + t->tv_delta.tv_sec = 0; + t->tv_delta.tv_usec = 0; t->tsc = 0; t->aperf = 0; @@ -1573,6 +1587,9 @@ void compute_average(struct thread_data *t, struct core_data *c, for_all_cpus(sum_counters, t, c, p); + /* Use the global time delta for the average. */ + average.threads.tv_delta = tv_delta; + average.threads.tsc /= topo.num_cpus; average.threads.aperf /= topo.num_cpus; average.threads.mperf /= topo.num_cpus; @@ -1714,7 +1731,7 @@ void get_apic_id(struct thread_data *t) if (!DO_BIC(BIC_X2APIC)) return; - if (authentic_amd) { + if (authentic_amd || hygon_genuine) { unsigned int topology_extensions; if (max_extended_level < 0x8000001e) @@ -1762,19 +1779,20 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) struct msr_counter *mp; int i; - gettimeofday(&t->tv_begin, (struct timezone *)NULL); - if (cpu_migrate(cpu)) { fprintf(outf, "Could not migrate to CPU %d\n", cpu); return -1; } + gettimeofday(&t->tv_begin, (struct timezone *)NULL); + if (first_counter_read) get_apic_id(t); retry: t->tsc = rdtsc(); /* we are running on local CPU of interest */ - if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz)) { + if (DO_BIC(BIC_Avg_MHz) || DO_BIC(BIC_Busy) || DO_BIC(BIC_Bzy_MHz) || + soft_c1_residency_display(BIC_Avg_MHz)) { unsigned long long tsc_before, tsc_between, tsc_after, aperf_time, mperf_time; /* @@ -1851,20 +1869,20 @@ retry: if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (DO_BIC(BIC_CPU_c3)) { + if (DO_BIC(BIC_CPU_c3) || soft_c1_residency_display(BIC_CPU_c3)) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; } - if (DO_BIC(BIC_CPU_c6) && !do_knl_cstates) { + if ((DO_BIC(BIC_CPU_c6) || soft_c1_residency_display(BIC_CPU_c6)) && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6)) return -7; - } else if (do_knl_cstates) { + } else if (do_knl_cstates || soft_c1_residency_display(BIC_CPU_c6)) { if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6)) return -7; } - if (DO_BIC(BIC_CPU_c7)) + if (DO_BIC(BIC_CPU_c7) || soft_c1_residency_display(BIC_CPU_c7)) if (get_msr(cpu, MSR_CORE_C7_RESIDENCY, &c->c7)) return -8; @@ -2912,6 +2930,7 @@ int snapshot_cpu_lpi_us(void) if (retval != 1) { fprintf(stderr, "Disabling Low Power Idle CPU output\n"); BIC_NOT_PRESENT(BIC_CPU_LPI); + fclose(fp); return -1; } @@ -2938,6 +2957,7 @@ int snapshot_sys_lpi_us(void) if (retval != 1) { fprintf(stderr, "Disabling Low Power Idle System output\n"); BIC_NOT_PRESENT(BIC_SYS_LPI); + fclose(fp); return -1; } fclose(fp); @@ -2985,8 +3005,6 @@ static void signal_handler (int signal) fprintf(stderr, "SIGUSR1\n"); break; } - /* make sure this manually-invoked interval is at least 1ms long */ - nanosleep(&one_msec, NULL); } void setup_signal_handler(void) @@ -3005,29 +3023,38 @@ void setup_signal_handler(void) void do_sleep(void) { - struct timeval select_timeout; + struct timeval tout; + struct timespec rest; fd_set readfds; int retval; FD_ZERO(&readfds); FD_SET(0, &readfds); - if (!isatty(fileno(stdin))) { + if (ignore_stdin) { nanosleep(&interval_ts, NULL); return; } - select_timeout = interval_tv; - retval = select(1, &readfds, NULL, NULL, &select_timeout); + tout = interval_tv; + retval = select(1, &readfds, NULL, NULL, &tout); if (retval == 1) { switch (getc(stdin)) { case 'q': exit_requested = 1; break; + case EOF: + /* + * 'stdin' is a pipe closed on the other end. There + * won't be any further input. + */ + ignore_stdin = 1; + /* Sleep the rest of the time */ + rest.tv_sec = (tout.tv_sec + tout.tv_usec / 1000000); + rest.tv_nsec = (tout.tv_usec % 1000000) * 1000; + nanosleep(&rest, NULL); } - /* make sure this manually-invoked interval is at least 1ms long */ - nanosleep(&one_msec, NULL); } } @@ -3209,6 +3236,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) break; case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSX */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ @@ -3405,6 +3433,7 @@ int has_config_tdp(unsigned int family, unsigned int model) case INTEL_FAM6_IVYBRIDGE: /* IVB */ case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSX */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ @@ -3803,6 +3832,7 @@ double get_tdp_amd(unsigned int family) { switch (family) { case 0x17: + case 0x18: default: /* This is the max stock TDP of HEDT/Server Fam17h chips */ return 250.0; @@ -3841,6 +3871,7 @@ void rapl_probe_intel(unsigned int family, unsigned int model) case INTEL_FAM6_SANDYBRIDGE: case INTEL_FAM6_IVYBRIDGE: case INTEL_FAM6_HASWELL_CORE: /* HSW */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ @@ -3982,6 +4013,7 @@ void rapl_probe_amd(unsigned int family, unsigned int model) switch (family) { case 0x17: /* Zen, Zen+ */ + case 0x18: /* Hygon Dhyana */ do_rapl = RAPL_AMD_F17H | RAPL_PER_CORE_ENERGY; if (rapl_joules) { BIC_PRESENT(BIC_Pkg_J); @@ -4002,7 +4034,7 @@ void rapl_probe_amd(unsigned int family, unsigned int model) rapl_energy_units = ldexp(1.0, -(msr >> 8 & 0x1f)); rapl_power_units = ldexp(1.0, -(msr & 0xf)); - tdp = get_tdp_amd(model); + tdp = get_tdp_amd(family); rapl_joule_counter_range = 0xFFFFFFFF * rapl_energy_units / tdp; if (!quiet) @@ -4018,7 +4050,7 @@ void rapl_probe(unsigned int family, unsigned int model) { if (genuine_intel) rapl_probe_intel(family, model); - if (authentic_amd) + if (authentic_amd || hygon_genuine) rapl_probe_amd(family, model); } @@ -4032,6 +4064,7 @@ void perf_limit_reasons_probe(unsigned int family, unsigned int model) switch (model) { case INTEL_FAM6_HASWELL_CORE: /* HSW */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ do_gfx_perf_limit_reasons = 1; case INTEL_FAM6_HASWELL_X: /* HSX */ @@ -4251,6 +4284,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) case INTEL_FAM6_IVYBRIDGE_X: /* IVB Xeon */ case INTEL_FAM6_HASWELL_CORE: /* HSW */ case INTEL_FAM6_HASWELL_X: /* HSW */ + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_HASWELL_GT3E: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_BROADWELL_GT3E: /* BDW */ @@ -4267,7 +4301,7 @@ int has_snb_msrs(unsigned int family, unsigned int model) } /* - * HSW adds support for additional MSRs: + * HSW ULT added support for C8/C9/C10 MSRs: * * MSR_PKG_C8_RESIDENCY 0x00000630 * MSR_PKG_C9_RESIDENCY 0x00000631 @@ -4278,13 +4312,13 @@ int has_snb_msrs(unsigned int family, unsigned int model) * MSR_PKGC10_IRTL 0x00000635 * */ -int has_hsw_msrs(unsigned int family, unsigned int model) +int has_c8910_msrs(unsigned int family, unsigned int model) { if (!genuine_intel) return 0; switch (model) { - case INTEL_FAM6_HASWELL_CORE: + case INTEL_FAM6_HASWELL_ULT: /* HSW */ case INTEL_FAM6_BROADWELL_CORE: /* BDW */ case INTEL_FAM6_SKYLAKE_MOBILE: /* SKL */ case INTEL_FAM6_CANNONLAKE_MOBILE: /* CNL */ @@ -4568,9 +4602,6 @@ unsigned int intel_model_duplicates(unsigned int model) case INTEL_FAM6_XEON_PHI_KNM: return INTEL_FAM6_XEON_PHI_KNL; - case INTEL_FAM6_HASWELL_ULT: - return INTEL_FAM6_HASWELL_CORE; - case INTEL_FAM6_BROADWELL_X: case INTEL_FAM6_BROADWELL_XEON_D: /* BDX-DE */ return INTEL_FAM6_BROADWELL_X; @@ -4582,7 +4613,11 @@ unsigned int intel_model_duplicates(unsigned int model) return INTEL_FAM6_SKYLAKE_MOBILE; case INTEL_FAM6_ICELAKE_MOBILE: + case INTEL_FAM6_ICELAKE_NNPI: return INTEL_FAM6_CANNONLAKE_MOBILE; + + case INTEL_FAM6_ATOM_TREMONT_X: + return INTEL_FAM6_ATOM_GOLDMONT_X; } return model; } @@ -4600,6 +4635,8 @@ void process_cpuid() genuine_intel = 1; else if (ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65) authentic_amd = 1; + else if (ebx == 0x6f677948 && ecx == 0x656e6975 && edx == 0x6e65476e) + hygon_genuine = 1; if (!quiet) fprintf(outf, "CPUID(0): %.4s%.4s%.4s ", @@ -4820,12 +4857,12 @@ void process_cpuid() BIC_NOT_PRESENT(BIC_CPU_c7); BIC_NOT_PRESENT(BIC_Pkgpc7); } - if (has_hsw_msrs(family, model)) { + if (has_c8910_msrs(family, model)) { BIC_PRESENT(BIC_Pkgpc8); BIC_PRESENT(BIC_Pkgpc9); BIC_PRESENT(BIC_Pkgpc10); } - do_irtl_hsw = has_hsw_msrs(family, model); + do_irtl_hsw = has_c8910_msrs(family, model); if (has_skl_msrs(family, model)) { BIC_PRESENT(BIC_Totl_c0); BIC_PRESENT(BIC_Any_c0); @@ -5123,7 +5160,7 @@ int initialize_counters(int cpu_id) void allocate_output_buffer() { - output_buffer = calloc(1, (1 + topo.num_cpus) * 1024); + output_buffer = calloc(1, (1 + topo.num_cpus) * 2048); outp = output_buffer; if (outp == NULL) err(-1, "calloc output buffer"); @@ -5269,7 +5306,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(outf, "turbostat version 19.03.20" + fprintf(outf, "turbostat version 19.08.31" " - Len Brown <lenb@kernel.org>\n"); } diff --git a/tools/power/x86/x86_energy_perf_policy/Makefile b/tools/power/x86/x86_energy_perf_policy/Makefile index 1fdeef864e7c..666b325a62a2 100644 --- a/tools/power/x86/x86_energy_perf_policy/Makefile +++ b/tools/power/x86/x86_energy_perf_policy/Makefile @@ -9,8 +9,9 @@ ifeq ("$(origin O)", "command line") endif x86_energy_perf_policy : x86_energy_perf_policy.c -override CFLAGS += -Wall -I../../../include +override CFLAGS += -O2 -Wall -I../../../include override CFLAGS += -DMSRHEADER='"../../../../arch/x86/include/asm/msr-index.h"' +override CFLAGS += -D_FORTIFY_SOURCE=2 %: %.c @mkdir -p $(BUILD_OUTPUT) diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 index 17db1c3af4d0..78c6361898b1 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.8 @@ -40,7 +40,7 @@ in the same processor package. Hardware P-States (HWP) are effectively an expansion of hardware P-state control from the opportunistic turbo-mode P-state range to include the entire range of available P-states. -On Broadwell Xeon, the initial HWP implementation, EBP influenced HWP. +On Broadwell Xeon, the initial HWP implementation, EPB influenced HWP. That influence was removed in subsequent generations, where it was moved to the Energy_Performance_Preference (EPP) field in diff --git a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c index 34a796b303fe..3fe1eed900d4 100644 --- a/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c +++ b/tools/power/x86/x86_energy_perf_policy/x86_energy_perf_policy.c @@ -545,7 +545,7 @@ void cmdline(int argc, char **argv) progname = argv[0]; - while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw", + while ((opt = getopt_long_only(argc, argv, "+a:c:dD:E:e:f:m:M:rt:u:vw:", long_options, &option_index)) != -1) { switch (opt) { case 'a': @@ -1259,6 +1259,15 @@ void probe_dev_msr(void) if (system("/sbin/modprobe msr > /dev/null 2>&1")) err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); } + +static void get_cpuid_or_exit(unsigned int leaf, + unsigned int *eax, unsigned int *ebx, + unsigned int *ecx, unsigned int *edx) +{ + if (!__get_cpuid(leaf, eax, ebx, ecx, edx)) + errx(1, "Processor not supported\n"); +} + /* * early_cpuid() * initialize turbo_is_enabled, has_hwp, has_epb @@ -1266,15 +1275,10 @@ void probe_dev_msr(void) */ void early_cpuid(void) { - unsigned int eax, ebx, ecx, edx, max_level; + unsigned int eax, ebx, ecx, edx; unsigned int fms, family, model; - __get_cpuid(0, &max_level, &ebx, &ecx, &edx); - - if (max_level < 6) - errx(1, "Processor not supported\n"); - - __get_cpuid(1, &fms, &ebx, &ecx, &edx); + get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx); family = (fms >> 8) & 0xf; model = (fms >> 4) & 0xf; if (family == 6 || family == 0xf) @@ -1288,7 +1292,7 @@ void early_cpuid(void) bdx_highest_ratio = msr & 0xFF; } - __get_cpuid(0x6, &eax, &ebx, &ecx, &edx); + get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx); turbo_is_enabled = (eax >> 1) & 1; has_hwp = (eax >> 7) & 1; has_epb = (ecx >> 3) & 1; @@ -1306,7 +1310,7 @@ void parse_cpuid(void) eax = ebx = ecx = edx = 0; - __get_cpuid(0, &max_level, &ebx, &ecx, &edx); + get_cpuid_or_exit(0, &max_level, &ebx, &ecx, &edx); if (ebx == 0x756e6547 && edx == 0x49656e69 && ecx == 0x6c65746e) genuine_intel = 1; @@ -1315,7 +1319,7 @@ void parse_cpuid(void) fprintf(stderr, "CPUID(0): %.4s%.4s%.4s ", (char *)&ebx, (char *)&edx, (char *)&ecx); - __get_cpuid(1, &fms, &ebx, &ecx, &edx); + get_cpuid_or_exit(1, &fms, &ebx, &ecx, &edx); family = (fms >> 8) & 0xf; model = (fms >> 4) & 0xf; stepping = fms & 0xf; @@ -1340,7 +1344,7 @@ void parse_cpuid(void) errx(1, "CPUID: no MSR"); - __get_cpuid(0x6, &eax, &ebx, &ecx, &edx); + get_cpuid_or_exit(0x6, &eax, &ebx, &ecx, &edx); /* turbo_is_enabled already set */ /* has_hwp already set */ has_hwp_notify = eax & (1 << 8); diff --git a/tools/testing/selftests/arm64/.gitignore b/tools/testing/selftests/arm64/.gitignore new file mode 100644 index 000000000000..e8fae8d61ed6 --- /dev/null +++ b/tools/testing/selftests/arm64/.gitignore @@ -0,0 +1 @@ +tags_test diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile new file mode 100644 index 000000000000..a61b2e743e99 --- /dev/null +++ b/tools/testing/selftests/arm64/Makefile @@ -0,0 +1,11 @@ +# SPDX-License-Identifier: GPL-2.0 + +# ARCH can be overridden by the user for cross compiling +ARCH ?= $(shell uname -m 2>/dev/null || echo not) + +ifneq (,$(filter $(ARCH),aarch64 arm64)) +TEST_GEN_PROGS := tags_test +TEST_PROGS := run_tags_test.sh +endif + +include ../lib.mk diff --git a/tools/testing/selftests/arm64/run_tags_test.sh b/tools/testing/selftests/arm64/run_tags_test.sh new file mode 100755 index 000000000000..745f11379930 --- /dev/null +++ b/tools/testing/selftests/arm64/run_tags_test.sh @@ -0,0 +1,12 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 + +echo "--------------------" +echo "running tags test" +echo "--------------------" +./tags_test +if [ $? -ne 0 ]; then + echo "[FAIL]" +else + echo "[PASS]" +fi diff --git a/tools/testing/selftests/arm64/tags_test.c b/tools/testing/selftests/arm64/tags_test.c new file mode 100644 index 000000000000..5701163460ef --- /dev/null +++ b/tools/testing/selftests/arm64/tags_test.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <stdio.h> +#include <stdlib.h> +#include <unistd.h> +#include <stdint.h> +#include <sys/prctl.h> +#include <sys/utsname.h> + +#define SHIFT_TAG(tag) ((uint64_t)(tag) << 56) +#define SET_TAG(ptr, tag) (((uint64_t)(ptr) & ~SHIFT_TAG(0xff)) | \ + SHIFT_TAG(tag)) + +int main(void) +{ + static int tbi_enabled = 0; + unsigned long tag = 0; + struct utsname *ptr; + int err; + + if (prctl(PR_SET_TAGGED_ADDR_CTRL, PR_TAGGED_ADDR_ENABLE, 0, 0, 0) == 0) + tbi_enabled = 1; + ptr = (struct utsname *)malloc(sizeof(*ptr)); + if (tbi_enabled) + tag = 0x42; + ptr = (struct utsname *)SET_TAG(ptr, tag); + err = uname(ptr); + free(ptr); + + return err; +} diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index c085964e1d05..96752ebd938f 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -34,6 +34,9 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test BPF_OBJ_FILES = $(patsubst %.c,%.o, $(notdir $(wildcard progs/*.c))) TEST_GEN_FILES = $(BPF_OBJ_FILES) +BTF_C_FILES = $(wildcard progs/btf_dump_test_case_*.c) +TEST_FILES = $(BTF_C_FILES) + # Also test sub-register code-gen if LLVM has eBPF v3 processor support which # contains both ALU32 and JMP32 instructions. SUBREG_CODEGEN := $(shell echo "int cal(int a) { return a > 0; }" | \ @@ -68,7 +71,8 @@ TEST_PROGS := test_kmod.sh \ TEST_PROGS_EXTENDED := with_addr.sh \ with_tunnels.sh \ tcp_client.py \ - tcp_server.py + tcp_server.py \ + test_xdp_vlan.sh # Compile but not part of 'make run_tests' TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \ diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config index f7a0744db31e..5dc109f4c097 100644 --- a/tools/testing/selftests/bpf/config +++ b/tools/testing/selftests/bpf/config @@ -34,3 +34,4 @@ CONFIG_NET_MPLS_GSO=m CONFIG_MPLS_ROUTING=m CONFIG_MPLS_IPTUNNEL=m CONFIG_IPV6_SIT=m +CONFIG_BPF_JIT=y diff --git a/tools/testing/selftests/bpf/test_btf_dump.c b/tools/testing/selftests/bpf/test_btf_dump.c index 8f850823d35f..6e75dd3cb14f 100644 --- a/tools/testing/selftests/bpf/test_btf_dump.c +++ b/tools/testing/selftests/bpf/test_btf_dump.c @@ -97,6 +97,13 @@ int test_btf_dump_case(int n, struct btf_dump_test_case *test_case) } snprintf(test_file, sizeof(test_file), "progs/%s.c", test_case->name); + if (access(test_file, R_OK) == -1) + /* + * When the test is run with O=, kselftest copies TEST_FILES + * without preserving the directory structure. + */ + snprintf(test_file, sizeof(test_file), "%s.c", + test_case->name); /* * Diff test output and expected test output, contained between * START-EXPECTED-OUTPUT and END-EXPECTED-OUTPUT lines in test case. diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c index 2fc4625c1a15..655729004391 100644 --- a/tools/testing/selftests/bpf/test_cgroup_storage.c +++ b/tools/testing/selftests/bpf/test_cgroup_storage.c @@ -20,9 +20,9 @@ int main(int argc, char **argv) BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage), - BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0), BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, 0x1), - BPF_STX_MEM(BPF_W, BPF_REG_0, BPF_REG_3, 0), + BPF_STX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0), BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */ BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */ @@ -30,7 +30,7 @@ int main(int argc, char **argv) BPF_FUNC_get_local_storage), BPF_MOV64_IMM(BPF_REG_1, 1), BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0), - BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0), + BPF_LDX_MEM(BPF_DW, BPF_REG_1, BPF_REG_0, 0), BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1), BPF_MOV64_REG(BPF_REG_0, BPF_REG_1), BPF_EXIT_INSN(), diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c index fb679ac3d4b0..0e6652733462 100644 --- a/tools/testing/selftests/bpf/test_sock.c +++ b/tools/testing/selftests/bpf/test_sock.c @@ -13,6 +13,7 @@ #include <bpf/bpf.h> #include "cgroup_helpers.h" +#include "bpf_endian.h" #include "bpf_rlimit.h" #include "bpf_util.h" @@ -232,7 +233,8 @@ static struct sock_test tests[] = { /* if (ip == expected && port == expected) */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock, src_ip6[3])), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x01000000, 4), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x00000001), 4), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock, src_port)), BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x2001, 2), @@ -261,7 +263,8 @@ static struct sock_test tests[] = { /* if (ip == expected && port == expected) */ BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock, src_ip4)), - BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x0100007F, 4), + BPF_JMP_IMM(BPF_JNE, BPF_REG_7, + __bpf_constant_ntohl(0x7F000001), 4), BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_6, offsetof(struct bpf_sock, src_port)), BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x1002, 2), diff --git a/tools/testing/selftests/cgroup/test_freezer.c b/tools/testing/selftests/cgroup/test_freezer.c index 8219a30853d2..0fc1b6d4b0f9 100644 --- a/tools/testing/selftests/cgroup/test_freezer.c +++ b/tools/testing/selftests/cgroup/test_freezer.c @@ -448,6 +448,59 @@ cleanup: } /* + * The test creates a cgroups and freezes it. Then it creates a child cgroup + * and populates it with a task. After that it checks that the child cgroup + * is frozen and the parent cgroup remains frozen too. + */ +static int test_cgfreezer_mkdir(const char *root) +{ + int ret = KSFT_FAIL; + char *parent, *child = NULL; + int pid; + + parent = cg_name(root, "cg_test_mkdir_A"); + if (!parent) + goto cleanup; + + child = cg_name(parent, "cg_test_mkdir_B"); + if (!child) + goto cleanup; + + if (cg_create(parent)) + goto cleanup; + + if (cg_freeze_wait(parent, true)) + goto cleanup; + + if (cg_create(child)) + goto cleanup; + + pid = cg_run_nowait(child, child_fn, NULL); + if (pid < 0) + goto cleanup; + + if (cg_wait_for_proc_count(child, 1)) + goto cleanup; + + if (cg_check_frozen(child, true)) + goto cleanup; + + if (cg_check_frozen(parent, true)) + goto cleanup; + + ret = KSFT_PASS; + +cleanup: + if (child) + cg_destroy(child); + free(child); + if (parent) + cg_destroy(parent); + free(parent); + return ret; +} + +/* * The test creates two nested cgroups, freezes the parent * and removes the child. Then it checks that the parent cgroup * remains frozen and it's possible to create a new child @@ -815,6 +868,7 @@ struct cgfreezer_test { T(test_cgfreezer_simple), T(test_cgfreezer_tree), T(test_cgfreezer_forkbomb), + T(test_cgfreezer_mkdir), T(test_cgfreezer_rmdir), T(test_cgfreezer_migrate), T(test_cgfreezer_ptrace), diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh index c5c93d5fb3ad..f9ebeac1e6f2 100755 --- a/tools/testing/selftests/net/fib_nexthops.sh +++ b/tools/testing/selftests/net/fib_nexthops.sh @@ -212,6 +212,8 @@ check_output() printf " ${out}\n" printf " Expected:\n" printf " ${expected}\n\n" + else + echo " WARNING: Unexpected route entry" fi fi @@ -274,7 +276,7 @@ ipv6_fcnal() run_cmd "$IP nexthop get id 52" log_test $? 0 "Get nexthop by id" - check_nexthop "id 52" "id 52 via 2001:db8:91::2 dev veth1" + check_nexthop "id 52" "id 52 via 2001:db8:91::2 dev veth1 scope link" run_cmd "$IP nexthop del id 52" log_test $? 0 "Delete nexthop by id" @@ -479,12 +481,12 @@ ipv6_fcnal_runtime() run_cmd "$IP -6 nexthop add id 85 dev veth1" run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 85" log_test $? 0 "IPv6 route with device only nexthop" - check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1" + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 dev veth1 metric 1024 pref medium" run_cmd "$IP nexthop add id 123 group 81/85" run_cmd "$IP ro replace 2001:db8:101::1/128 nhid 123" log_test $? 0 "IPv6 multipath route with nexthop mix - dev only + gw" - check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 85 nexthop via 2001:db8:91::2 dev veth1 nexthop dev veth1" + check_route6 "2001:db8:101::1" "2001:db8:101::1 nhid 123 metric 1024 nexthop via 2001:db8:91::2 dev veth1 weight 1 nexthop dev veth1 weight 1 pref medium" # # IPv6 route with v4 nexthop - not allowed @@ -538,7 +540,7 @@ ipv4_fcnal() run_cmd "$IP nexthop get id 12" log_test $? 0 "Get nexthop by id" - check_nexthop "id 12" "id 12 via 172.16.1.2 src 172.16.1.1 dev veth1 scope link" + check_nexthop "id 12" "id 12 via 172.16.1.2 dev veth1 scope link" run_cmd "$IP nexthop del id 12" log_test $? 0 "Delete nexthop by id" @@ -685,7 +687,7 @@ ipv4_withv6_fcnal() set +e run_cmd "$IP ro add 172.16.101.1/32 nhid 11" log_test $? 0 "IPv6 nexthop with IPv4 route" - check_route "172.16.101.1" "172.16.101.1 nhid 11 via ${lladdr} dev veth1" + check_route "172.16.101.1" "172.16.101.1 nhid 11 via inet6 ${lladdr} dev veth1" set -e run_cmd "$IP nexthop add id 12 via 172.16.1.2 dev veth1" @@ -694,11 +696,11 @@ ipv4_withv6_fcnal() run_cmd "$IP ro replace 172.16.101.1/32 nhid 101" log_test $? 0 "IPv6 nexthop with IPv4 route" - check_route "172.16.101.1" "172.16.101.1 nhid 101 nexthop via ${lladdr} dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1" + check_route "172.16.101.1" "172.16.101.1 nhid 101 nexthop via inet6 ${lladdr} dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1" run_cmd "$IP ro replace 172.16.101.1/32 via inet6 ${lladdr} dev veth1" log_test $? 0 "IPv4 route with IPv6 gateway" - check_route "172.16.101.1" "172.16.101.1 via ${lladdr} dev veth1" + check_route "172.16.101.1" "172.16.101.1 via inet6 ${lladdr} dev veth1" run_cmd "$IP ro replace 172.16.101.1/32 via inet6 2001:db8:50::1 dev veth1" log_test $? 2 "IPv4 route with invalid IPv6 gateway" @@ -785,10 +787,10 @@ ipv4_fcnal_runtime() log_test $? 0 "IPv4 route with device only nexthop" check_route "172.16.101.1" "172.16.101.1 nhid 85 dev veth1" - run_cmd "$IP nexthop add id 122 group 21/85" - run_cmd "$IP ro replace 172.16.101.1/32 nhid 122" + run_cmd "$IP nexthop add id 123 group 21/85" + run_cmd "$IP ro replace 172.16.101.1/32 nhid 123" log_test $? 0 "IPv4 multipath route with nexthop mix - dev only + gw" - check_route "172.16.101.1" "172.16.101.1 nhid 85 nexthop via 172.16.1.2 dev veth1 nexthop dev veth1" + check_route "172.16.101.1" "172.16.101.1 nhid 123 nexthop via 172.16.1.2 dev veth1 weight 1 nexthop dev veth1 weight 1" # # IPv4 with IPv6 @@ -820,7 +822,7 @@ ipv4_fcnal_runtime() run_cmd "$IP ro replace 172.16.101.1/32 nhid 101" log_test $? 0 "IPv4 route with mixed v4-v6 multipath route" - check_route "172.16.101.1" "172.16.101.1 nhid 101 nexthop via ${lladdr} dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1" + check_route "172.16.101.1" "172.16.101.1 nhid 101 nexthop via inet6 ${lladdr} dev veth1 weight 1 nexthop via 172.16.1.2 dev veth1 weight 1" run_cmd "ip netns exec me ping -c1 -w1 172.16.101.1" log_test $? 0 "IPv6 nexthop with IPv4 route" diff --git a/tools/testing/selftests/net/xfrm_policy.sh b/tools/testing/selftests/net/xfrm_policy.sh index 5445943bf07f..7a1bf94c5bd3 100755 --- a/tools/testing/selftests/net/xfrm_policy.sh +++ b/tools/testing/selftests/net/xfrm_policy.sh @@ -106,6 +106,13 @@ do_overlap() # # 10.0.0.0/24 and 10.0.1.0/24 nodes have been merged as 10.0.0.0/23. ip -net $ns xfrm policy add src 10.1.0.0/24 dst 10.0.0.0/23 dir fwd priority 200 action block + + # similar to above: add policies (with partially random address), with shrinking prefixes. + for p in 29 28 27;do + for k in $(seq 1 32); do + ip -net $ns xfrm policy add src 10.253.1.$((RANDOM%255))/$p dst 10.254.1.$((RANDOM%255))/$p dir fwd priority $((200+k)) action block 2>/dev/null + done + done } do_esp_policy_get_check() { diff --git a/tools/testing/selftests/pidfd/.gitignore b/tools/testing/selftests/pidfd/.gitignore index 16d84d117bc0..8d069490e17b 100644 --- a/tools/testing/selftests/pidfd/.gitignore +++ b/tools/testing/selftests/pidfd/.gitignore @@ -1,2 +1,4 @@ pidfd_open_test +pidfd_poll_test pidfd_test +pidfd_wait diff --git a/tools/testing/selftests/pidfd/Makefile b/tools/testing/selftests/pidfd/Makefile index 720b2d884b3c..464c9b76148f 100644 --- a/tools/testing/selftests/pidfd/Makefile +++ b/tools/testing/selftests/pidfd/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only CFLAGS += -g -I../../../../usr/include/ -lpthread -TEST_GEN_PROGS := pidfd_test pidfd_open_test +TEST_GEN_PROGS := pidfd_test pidfd_open_test pidfd_poll_test pidfd_wait include ../lib.mk diff --git a/tools/testing/selftests/pidfd/pidfd.h b/tools/testing/selftests/pidfd/pidfd.h index 8452e910463f..c6bc68329f4b 100644 --- a/tools/testing/selftests/pidfd/pidfd.h +++ b/tools/testing/selftests/pidfd/pidfd.h @@ -16,6 +16,26 @@ #include "../kselftest.h" +#ifndef P_PIDFD +#define P_PIDFD 3 +#endif + +#ifndef CLONE_PIDFD +#define CLONE_PIDFD 0x00001000 +#endif + +#ifndef __NR_pidfd_open +#define __NR_pidfd_open -1 +#endif + +#ifndef __NR_pidfd_send_signal +#define __NR_pidfd_send_signal -1 +#endif + +#ifndef __NR_clone3 +#define __NR_clone3 -1 +#endif + /* * The kernel reserves 300 pids via RESERVED_PIDS in kernel/pid.c * That means, when it wraps around any pid < 300 will be skipped. @@ -53,5 +73,15 @@ again: return WEXITSTATUS(status); } +static inline int sys_pidfd_open(pid_t pid, unsigned int flags) +{ + return syscall(__NR_pidfd_open, pid, flags); +} + +static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, + unsigned int flags) +{ + return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); +} #endif /* __PIDFD_H */ diff --git a/tools/testing/selftests/pidfd/pidfd_open_test.c b/tools/testing/selftests/pidfd/pidfd_open_test.c index 0377133dd6dc..b9fe75fc3e51 100644 --- a/tools/testing/selftests/pidfd/pidfd_open_test.c +++ b/tools/testing/selftests/pidfd/pidfd_open_test.c @@ -22,11 +22,6 @@ #include "pidfd.h" #include "../kselftest.h" -static inline int sys_pidfd_open(pid_t pid, unsigned int flags) -{ - return syscall(__NR_pidfd_open, pid, flags); -} - static int safe_int(const char *numstr, int *converted) { char *err = NULL; diff --git a/tools/testing/selftests/pidfd/pidfd_poll_test.c b/tools/testing/selftests/pidfd/pidfd_poll_test.c new file mode 100644 index 000000000000..4b115444dfe9 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_poll_test.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE +#include <errno.h> +#include <linux/types.h> +#include <linux/wait.h> +#include <poll.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <syscall.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "pidfd.h" +#include "../kselftest.h" + +static bool timeout; + +static void handle_alarm(int sig) +{ + timeout = true; +} + +int main(int argc, char **argv) +{ + struct pollfd fds; + int iter, nevents; + int nr_iterations = 10000; + + fds.events = POLLIN; + + if (argc > 2) + ksft_exit_fail_msg("Unexpected command line argument\n"); + + if (argc == 2) { + nr_iterations = atoi(argv[1]); + if (nr_iterations <= 0) + ksft_exit_fail_msg("invalid input parameter %s\n", + argv[1]); + } + + ksft_print_msg("running pidfd poll test for %d iterations\n", + nr_iterations); + + for (iter = 0; iter < nr_iterations; iter++) { + int pidfd; + int child_pid = fork(); + + if (child_pid < 0) { + if (errno == EAGAIN) { + iter--; + continue; + } + ksft_exit_fail_msg( + "%s - failed to fork a child process\n", + strerror(errno)); + } + + if (child_pid == 0) { + /* Child process just sleeps for a min and exits */ + sleep(60); + exit(EXIT_SUCCESS); + } + + /* Parent kills the child and waits for its death */ + pidfd = sys_pidfd_open(child_pid, 0); + if (pidfd < 0) + ksft_exit_fail_msg("%s - pidfd_open failed\n", + strerror(errno)); + + /* Setup 3 sec alarm - plenty of time */ + if (signal(SIGALRM, handle_alarm) == SIG_ERR) + ksft_exit_fail_msg("%s - signal failed\n", + strerror(errno)); + alarm(3); + + /* Send SIGKILL to the child */ + if (sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0)) + ksft_exit_fail_msg("%s - pidfd_send_signal failed\n", + strerror(errno)); + + /* Wait for the death notification */ + fds.fd = pidfd; + nevents = poll(&fds, 1, -1); + + /* Check for error conditions */ + if (nevents < 0) + ksft_exit_fail_msg("%s - poll failed\n", + strerror(errno)); + + if (nevents != 1) + ksft_exit_fail_msg("unexpected poll result: %d\n", + nevents); + + if (!(fds.revents & POLLIN)) + ksft_exit_fail_msg( + "unexpected event type received: 0x%x\n", + fds.revents); + + if (timeout) + ksft_exit_fail_msg( + "death notification wait timeout\n"); + + close(pidfd); + /* Wait for child to prevent zombies */ + if (waitpid(child_pid, NULL, 0) < 0) + ksft_exit_fail_msg("%s - waitpid failed\n", + strerror(errno)); + + } + + ksft_test_result_pass("pidfd poll test: pass\n"); + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/pidfd/pidfd_test.c b/tools/testing/selftests/pidfd/pidfd_test.c index b632965e60eb..7aff2d3b42c0 100644 --- a/tools/testing/selftests/pidfd/pidfd_test.c +++ b/tools/testing/selftests/pidfd/pidfd_test.c @@ -21,20 +21,12 @@ #include "pidfd.h" #include "../kselftest.h" -#ifndef __NR_pidfd_send_signal -#define __NR_pidfd_send_signal -1 -#endif - #define str(s) _str(s) #define _str(s) #s #define CHILD_THREAD_MIN_WAIT 3 /* seconds */ #define MAX_EVENTS 5 -#ifndef CLONE_PIDFD -#define CLONE_PIDFD 0x00001000 -#endif - static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *)) { size_t stack_size = 1024; @@ -47,12 +39,6 @@ static pid_t pidfd_clone(int flags, int *pidfd, int (*fn)(void *)) #endif } -static inline int sys_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, - unsigned int flags) -{ - return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); -} - static int signal_received; static void set_signal_received_on_sigusr1(int sig) diff --git a/tools/testing/selftests/pidfd/pidfd_wait.c b/tools/testing/selftests/pidfd/pidfd_wait.c new file mode 100644 index 000000000000..7079f8eef792 --- /dev/null +++ b/tools/testing/selftests/pidfd/pidfd_wait.c @@ -0,0 +1,271 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#define _GNU_SOURCE +#include <errno.h> +#include <linux/sched.h> +#include <linux/types.h> +#include <signal.h> +#include <stdint.h> +#include <stdio.h> +#include <stdlib.h> +#include <sched.h> +#include <string.h> +#include <sys/resource.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +#include "pidfd.h" +#include "../kselftest.h" + +#define ptr_to_u64(ptr) ((__u64)((uintptr_t)(ptr))) + +static pid_t sys_clone3(struct clone_args *args) +{ + return syscall(__NR_clone3, args, sizeof(struct clone_args)); +} + +static int sys_waitid(int which, pid_t pid, siginfo_t *info, int options, + struct rusage *ru) +{ + return syscall(__NR_waitid, which, pid, info, options, ru); +} + +static int test_pidfd_wait_simple(void) +{ + const char *test_name = "pidfd wait simple"; + int pidfd = -1, status = 0; + pid_t parent_tid = -1; + struct clone_args args = { + .parent_tid = ptr_to_u64(&parent_tid), + .pidfd = ptr_to_u64(&pidfd), + .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, + .exit_signal = SIGCHLD, + }; + int ret; + pid_t pid; + siginfo_t info = { + .si_signo = 0, + }; + + pidfd = open("/proc/self", O_DIRECTORY | O_RDONLY | O_CLOEXEC); + if (pidfd < 0) + ksft_exit_fail_msg("%s test: failed to open /proc/self %s\n", + test_name, strerror(errno)); + + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + if (pid == 0) + ksft_exit_fail_msg( + "%s test: succeeded to wait on invalid pidfd %s\n", + test_name, strerror(errno)); + close(pidfd); + pidfd = -1; + + pidfd = open("/dev/null", O_RDONLY | O_CLOEXEC); + if (pidfd == 0) + ksft_exit_fail_msg("%s test: failed to open /dev/null %s\n", + test_name, strerror(errno)); + + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + if (pid == 0) + ksft_exit_fail_msg( + "%s test: succeeded to wait on invalid pidfd %s\n", + test_name, strerror(errno)); + close(pidfd); + pidfd = -1; + + pid = sys_clone3(&args); + if (pid < 0) + ksft_exit_fail_msg("%s test: failed to create new process %s\n", + test_name, strerror(errno)); + + if (pid == 0) + exit(EXIT_SUCCESS); + + pid = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + if (pid < 0) + ksft_exit_fail_msg( + "%s test: failed to wait on process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (!WIFEXITED(info.si_status) || WEXITSTATUS(info.si_status)) + ksft_exit_fail_msg( + "%s test: unexpected status received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + close(pidfd); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_EXITED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + ksft_test_result_pass("%s test: Passed\n", test_name); + return 0; +} + +static int test_pidfd_wait_states(void) +{ + const char *test_name = "pidfd wait states"; + int pidfd = -1, status = 0; + pid_t parent_tid = -1; + struct clone_args args = { + .parent_tid = ptr_to_u64(&parent_tid), + .pidfd = ptr_to_u64(&pidfd), + .flags = CLONE_PIDFD | CLONE_PARENT_SETTID, + .exit_signal = SIGCHLD, + }; + int ret; + pid_t pid; + siginfo_t info = { + .si_signo = 0, + }; + + pid = sys_clone3(&args); + if (pid < 0) + ksft_exit_fail_msg("%s test: failed to create new process %s\n", + test_name, strerror(errno)); + + if (pid == 0) { + kill(getpid(), SIGSTOP); + kill(getpid(), SIGSTOP); + exit(EXIT_SUCCESS); + } + + ret = sys_waitid(P_PIDFD, pidfd, &info, WSTOPPED, NULL); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to wait on WSTOPPED process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_STOPPED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + ret = sys_pidfd_send_signal(pidfd, SIGCONT, NULL, 0); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to send signal to process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + ret = sys_waitid(P_PIDFD, pidfd, &info, WCONTINUED, NULL); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to wait WCONTINUED on process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_CONTINUED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + ret = sys_waitid(P_PIDFD, pidfd, &info, WUNTRACED, NULL); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to wait on WUNTRACED process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_STOPPED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + ret = sys_pidfd_send_signal(pidfd, SIGKILL, NULL, 0); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to send SIGKILL to process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + ret = sys_waitid(P_PIDFD, pidfd, &info, WEXITED, NULL); + if (ret < 0) + ksft_exit_fail_msg( + "%s test: failed to wait on WEXITED process with pid %d and pidfd %d: %s\n", + test_name, parent_tid, pidfd, strerror(errno)); + + if (info.si_signo != SIGCHLD) + ksft_exit_fail_msg( + "%s test: unexpected si_signo value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_signo, parent_tid, pidfd, + strerror(errno)); + + if (info.si_code != CLD_KILLED) + ksft_exit_fail_msg( + "%s test: unexpected si_code value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_code, parent_tid, pidfd, + strerror(errno)); + + if (info.si_pid != parent_tid) + ksft_exit_fail_msg( + "%s test: unexpected si_pid value %d received after waiting on process with pid %d and pidfd %d: %s\n", + test_name, info.si_pid, parent_tid, pidfd, + strerror(errno)); + + close(pidfd); + + ksft_test_result_pass("%s test: Passed\n", test_name); + return 0; +} + +int main(int argc, char **argv) +{ + ksft_print_header(); + ksft_set_plan(2); + + test_pidfd_wait_simple(); + test_pidfd_wait_states(); + + return ksft_exit_pass(); +} diff --git a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py index affa7f2d9670..9539cffa9e5e 100644 --- a/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py +++ b/tools/testing/selftests/tc-testing/plugin-lib/nsPlugin.py @@ -64,7 +64,7 @@ class SubPlugin(TdcPlugin): cmdlist.insert(0, self.args.NAMES['NS']) cmdlist.insert(0, 'exec') cmdlist.insert(0, 'netns') - cmdlist.insert(0, 'ip') + cmdlist.insert(0, self.args.NAMES['IP']) else: pass @@ -78,16 +78,16 @@ class SubPlugin(TdcPlugin): return command def _ports_create(self): - cmd = 'ip link add $DEV0 type veth peer name $DEV1' + cmd = '$IP link add $DEV0 type veth peer name $DEV1' self._exec_cmd('pre', cmd) - cmd = 'ip link set $DEV0 up' + cmd = '$IP link set $DEV0 up' self._exec_cmd('pre', cmd) if not self.args.namespace: - cmd = 'ip link set $DEV1 up' + cmd = '$IP link set $DEV1 up' self._exec_cmd('pre', cmd) def _ports_destroy(self): - cmd = 'ip link del $DEV0' + cmd = '$IP link del $DEV0' self._exec_cmd('post', cmd) def _ns_create(self): @@ -97,16 +97,16 @@ class SubPlugin(TdcPlugin): ''' self._ports_create() if self.args.namespace: - cmd = 'ip netns add {}'.format(self.args.NAMES['NS']) + cmd = '$IP netns add {}'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) - cmd = 'ip link set $DEV1 netns {}'.format(self.args.NAMES['NS']) + cmd = '$IP link set $DEV1 netns {}'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) - cmd = 'ip -n {} link set $DEV1 up'.format(self.args.NAMES['NS']) + cmd = '$IP -n {} link set $DEV1 up'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) if self.args.device: - cmd = 'ip link set $DEV2 netns {}'.format(self.args.NAMES['NS']) + cmd = '$IP link set $DEV2 netns {}'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) - cmd = 'ip -n {} link set $DEV2 up'.format(self.args.NAMES['NS']) + cmd = '$IP -n {} link set $DEV2 up'.format(self.args.NAMES['NS']) self._exec_cmd('pre', cmd) def _ns_destroy(self): @@ -115,7 +115,7 @@ class SubPlugin(TdcPlugin): devices as well) ''' if self.args.namespace: - cmd = 'ip netns delete {}'.format(self.args.NAMES['NS']) + cmd = '$IP netns delete {}'.format(self.args.NAMES['NS']) self._exec_cmd('post', cmd) def _exec_cmd(self, stage, command): |