diff options
Diffstat (limited to 'tools')
76 files changed, 1977 insertions, 661 deletions
diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 100ad3dc091a..3feac0482fe9 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -196,22 +196,22 @@ static int get_family_id(int sd) static void print_delayacct(struct taskstats *t) { - printf("\n\nCPU %15s%15s%15s%15s%15s%15s\n" - " %15llu%15llu%15llu%15llu%15.3fms%13.6fms\n" - "IO %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "SWAP %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "RECLAIM %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "THRASHING%12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "COMPACT %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "WPCOPY %12s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n" - "IRQ %15s%15s%15s%15s\n" - " %15llu%15llu%15.3fms%13.6fms\n", + printf("\n\nCPU %15s%15s%15s%15s%15s%15s%15s\n" + " %15llu%15llu%15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "IO %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "SWAP %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "RECLAIM %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "THRASHING%12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "COMPACT %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "WPCOPY %12s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n" + "IRQ %15s%15s%15s%15s%15s\n" + " %15llu%15llu%15.3fms%13.6fms%13.6fms\n", "count", "real total", "virtual total", "delay total", "delay average", "delay max", "delay min", (unsigned long long)t->cpu_count, diff --git a/tools/mm/page-types.c b/tools/mm/page-types.c index bcac7ebfb51f..d7e5e8902af8 100644 --- a/tools/mm/page-types.c +++ b/tools/mm/page-types.c @@ -24,8 +24,8 @@ #include <signal.h> #include <inttypes.h> #include <sys/types.h> -#include <sys/errno.h> -#include <sys/fcntl.h> +#include <errno.h> +#include <fcntl.h> #include <sys/mount.h> #include <sys/statfs.h> #include <sys/mman.h> diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index e16cef160bc2..ce32cb35007d 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -95,7 +95,7 @@ ynl_err_walk(struct ynl_sock *ys, void *start, void *end, unsigned int off, ynl_attr_for_each_payload(start, data_len, attr) { astart_off = (char *)attr - (char *)start; - aend_off = astart_off + ynl_attr_data_len(attr); + aend_off = (char *)ynl_attr_data_end(attr) - (char *)start; if (aend_off <= off) continue; diff --git a/tools/objtool/check.c b/tools/objtool/check.c index 753dbc4f8198..be18a0489303 100644 --- a/tools/objtool/check.c +++ b/tools/objtool/check.c @@ -227,6 +227,7 @@ static bool is_rust_noreturn(const struct symbol *func) str_ends_with(func->name, "_4core9panicking18panic_bounds_check") || str_ends_with(func->name, "_4core9panicking19assert_failed_inner") || str_ends_with(func->name, "_4core9panicking36panic_misaligned_pointer_dereference") || + strstr(func->name, "_4core9panicking13assert_failed") || strstr(func->name, "_4core9panicking11panic_const24panic_const_") || (strstr(func->name, "_4core5slice5index24slice_") && str_ends_with(func->name, "_fail")); @@ -1975,6 +1976,14 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, reloc_addend(reloc) == pfunc->offset) break; + /* + * Clang sometimes leaves dangling unused jump table entries + * which point to the end of the function. Ignore them. + */ + if (reloc->sym->sec == pfunc->sec && + reloc_addend(reloc) == pfunc->offset + pfunc->len) + goto next; + dest_insn = find_insn(file, reloc->sym->sec, reloc_addend(reloc)); if (!dest_insn) break; @@ -1992,6 +2001,7 @@ static int add_jump_table(struct objtool_file *file, struct instruction *insn, alt->insn = dest_insn; alt->next = insn->alts; insn->alts = alt; +next: prev_offset = reloc_offset(reloc); } @@ -2264,7 +2274,7 @@ static int read_annotate(struct objtool_file *file, if (sec->sh.sh_entsize != 8) { static bool warned = false; - if (!warned) { + if (!warned && opts.verbose) { WARN("%s: dodgy linker, sh_entsize != 8", sec->name); warned = true; } diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index d7c7d29291fb..d466447ae928 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2107,8 +2107,12 @@ static int trace__read_syscall_info(struct trace *trace, int id) return PTR_ERR(sc->tp_format); } + /* + * The tracepoint format contains __syscall_nr field, so it's one more + * than the actual number of syscall arguments. + */ if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? - RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields)) + RAW_SYSCALL_ARGS_NUM : sc->tp_format->format.nr_fields - 1)) return -ENOMEM; sc->args = sc->tp_format->format.fields; diff --git a/tools/perf/tests/shell/trace_btf_enum.sh b/tools/perf/tests/shell/trace_btf_enum.sh index 5a3b8a5a9b5c..8d1e6bbeac90 100755 --- a/tools/perf/tests/shell/trace_btf_enum.sh +++ b/tools/perf/tests/shell/trace_btf_enum.sh @@ -26,8 +26,12 @@ check_vmlinux() { trace_landlock() { echo "Tracing syscall ${syscall}" - # test flight just to see if landlock_add_rule and libbpf are available - $TESTPROG + # test flight just to see if landlock_add_rule is available + if ! perf trace $TESTPROG 2>&1 | grep -q landlock + then + echo "No landlock system call found, skipping to non-syscall tracing." + return + fi if perf trace -e $syscall $TESTPROG 2>&1 | \ grep -q -E ".*landlock_add_rule\(ruleset_fd: 11, rule_type: (LANDLOCK_RULE_PATH_BENEATH|LANDLOCK_RULE_NET_PORT), rule_attr: 0x[a-f0-9]+, flags: 45\) = -1.*" diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index 0d2ea22bd9e4..31bb326b07a6 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2100,6 +2100,57 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel, return 0; } +const char * const perf_disassembler__strs[] = { + [PERF_DISASM_UNKNOWN] = "unknown", + [PERF_DISASM_LLVM] = "llvm", + [PERF_DISASM_CAPSTONE] = "capstone", + [PERF_DISASM_OBJDUMP] = "objdump", +}; + + +static void annotation_options__add_disassembler(struct annotation_options *options, + enum perf_disassembler dis) +{ + for (u8 i = 0; i < ARRAY_SIZE(options->disassemblers); i++) { + if (options->disassemblers[i] == dis) { + /* Disassembler is already present then don't add again. */ + return; + } + if (options->disassemblers[i] == PERF_DISASM_UNKNOWN) { + /* Found a free slot. */ + options->disassemblers[i] = dis; + return; + } + } + pr_err("Failed to add disassembler %d\n", dis); +} + +static int annotation_options__add_disassemblers_str(struct annotation_options *options, + const char *str) +{ + while (str && *str != '\0') { + const char *comma = strchr(str, ','); + int len = comma ? comma - str : (int)strlen(str); + bool match = false; + + for (u8 i = 0; i < ARRAY_SIZE(perf_disassembler__strs); i++) { + const char *dis_str = perf_disassembler__strs[i]; + + if (len == (int)strlen(dis_str) && !strncmp(str, dis_str, len)) { + annotation_options__add_disassembler(options, i); + match = true; + break; + } + } + if (!match) { + pr_err("Invalid disassembler '%.*s'\n", len, str); + return -1; + } + str = comma ? comma + 1 : NULL; + } + return 0; +} + static int annotation__config(const char *var, const char *value, void *data) { struct annotation_options *opt = data; @@ -2115,11 +2166,10 @@ static int annotation__config(const char *var, const char *value, void *data) else if (opt->offset_level < ANNOTATION__MIN_OFFSET_LEVEL) opt->offset_level = ANNOTATION__MIN_OFFSET_LEVEL; } else if (!strcmp(var, "annotate.disassemblers")) { - opt->disassemblers_str = strdup(value); - if (!opt->disassemblers_str) { - pr_err("Not enough memory for annotate.disassemblers\n"); - return -1; - } + int err = annotation_options__add_disassemblers_str(opt, value); + + if (err) + return err; } else if (!strcmp(var, "annotate.hide_src_code")) { opt->hide_src_code = perf_config_bool("hide_src_code", value); } else if (!strcmp(var, "annotate.jump_arrows")) { @@ -2185,9 +2235,25 @@ void annotation_options__exit(void) zfree(&annotate_opts.objdump_path); } +static void annotation_options__default_init_disassemblers(struct annotation_options *options) +{ + if (options->disassemblers[0] != PERF_DISASM_UNKNOWN) { + /* Already initialized. */ + return; + } +#ifdef HAVE_LIBLLVM_SUPPORT + annotation_options__add_disassembler(options, PERF_DISASM_LLVM); +#endif +#ifdef HAVE_LIBCAPSTONE_SUPPORT + annotation_options__add_disassembler(options, PERF_DISASM_CAPSTONE); +#endif + annotation_options__add_disassembler(options, PERF_DISASM_OBJDUMP); +} + void annotation_config__init(void) { perf_config(annotation__config, &annotate_opts); + annotation_options__default_init_disassemblers(&annotate_opts); } static unsigned int parse_percent_type(char *str1, char *str2) diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h index 0ba5846dad4d..98db1b88daf4 100644 --- a/tools/perf/util/annotate.h +++ b/tools/perf/util/annotate.h @@ -34,8 +34,13 @@ struct annotated_data_type; #define ANNOTATION__BR_CNTR_WIDTH 30 #define ANNOTATION_DUMMY_LEN 256 -// llvm, capstone, objdump -#define MAX_DISASSEMBLERS 3 +enum perf_disassembler { + PERF_DISASM_UNKNOWN = 0, + PERF_DISASM_LLVM, + PERF_DISASM_CAPSTONE, + PERF_DISASM_OBJDUMP, +}; +#define MAX_DISASSEMBLERS (PERF_DISASM_OBJDUMP + 1) struct annotation_options { bool hide_src_code, @@ -52,14 +57,12 @@ struct annotation_options { annotate_src, full_addr; u8 offset_level; - u8 nr_disassemblers; + u8 disassemblers[MAX_DISASSEMBLERS]; int min_pcnt; int max_lines; int context; char *objdump_path; char *disassembler_style; - const char *disassemblers_str; - const char *disassemblers[MAX_DISASSEMBLERS]; const char *prefix; const char *prefix_strip; unsigned int percent_type; @@ -134,6 +137,8 @@ struct disasm_line { struct annotation_line al; }; +extern const char * const perf_disassembler__strs[]; + void annotation_line__add(struct annotation_line *al, struct list_head *head); static inline double annotation_data__percent(struct annotation_data *data, diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c index 4a62ed593e84..e4352881e3fa 100644 --- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c +++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c @@ -431,9 +431,9 @@ static bool pid_filter__has(struct pids_filtered *pids, pid_t pid) static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) { bool augmented, do_output = false; - int zero = 0, size, aug_size, index, - value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); + int zero = 0, index, value_size = sizeof(struct augmented_arg) - offsetof(struct augmented_arg, value); u64 output = 0; /* has to be u64, otherwise it won't pass the verifier */ + s64 aug_size, size; unsigned int nr, *beauty_map; struct beauty_payload_enter *payload; void *arg, *payload_offset; @@ -484,14 +484,11 @@ static int augment_sys_enter(void *ctx, struct syscall_enter_args *args) } else if (size > 0 && size <= value_size) { /* struct */ if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, size, arg)) augmented = true; - } else if (size < 0 && size >= -6) { /* buffer */ + } else if ((int)size < 0 && size >= -6) { /* buffer */ index = -(size + 1); barrier_var(index); // Prevent clang (noticed with v18) from removing the &= 7 trick. index &= 7; // Satisfy the bounds checking with the verifier in some kernels. - aug_size = args->args[index]; - - if (aug_size > TRACE_AUG_MAX_BUF) - aug_size = TRACE_AUG_MAX_BUF; + aug_size = args->args[index] > TRACE_AUG_MAX_BUF ? TRACE_AUG_MAX_BUF : args->args[index]; if (aug_size > 0) { if (!bpf_probe_read_user(((struct augmented_arg *)payload_offset)->value, aug_size, arg)) diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c index 27094211edd8..5c329ad614e9 100644 --- a/tools/perf/util/cpumap.c +++ b/tools/perf/util/cpumap.c @@ -293,7 +293,7 @@ struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data) die = cpu__get_die_id(cpu); /* There is no die_id on legacy system. */ - if (die == -1) + if (die < 0) die = 0; /* @@ -322,7 +322,7 @@ struct aggr_cpu_id aggr_cpu_id__cluster(struct perf_cpu cpu, void *data) struct aggr_cpu_id id; /* There is no cluster_id on legacy system. */ - if (cluster == -1) + if (cluster < 0) cluster = 0; id = aggr_cpu_id__die(cpu, data); diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c index b7de4d9fd004..50c5c206b70e 100644 --- a/tools/perf/util/disasm.c +++ b/tools/perf/util/disasm.c @@ -2216,56 +2216,6 @@ out_free_command: return err; } -static int annotation_options__init_disassemblers(struct annotation_options *options) -{ - char *disassembler; - - if (options->disassemblers_str == NULL) { - const char *default_disassemblers_str = -#ifdef HAVE_LIBLLVM_SUPPORT - "llvm," -#endif -#ifdef HAVE_LIBCAPSTONE_SUPPORT - "capstone," -#endif - "objdump"; - - options->disassemblers_str = strdup(default_disassemblers_str); - if (!options->disassemblers_str) - goto out_enomem; - } - - disassembler = strdup(options->disassemblers_str); - if (disassembler == NULL) - goto out_enomem; - - while (1) { - char *comma = strchr(disassembler, ','); - - if (comma != NULL) - *comma = '\0'; - - options->disassemblers[options->nr_disassemblers++] = strim(disassembler); - - if (comma == NULL) - break; - - disassembler = comma + 1; - - if (options->nr_disassemblers >= MAX_DISASSEMBLERS) { - pr_debug("annotate.disassemblers can have at most %d entries, ignoring \"%s\"\n", - MAX_DISASSEMBLERS, disassembler); - break; - } - } - - return 0; - -out_enomem: - pr_err("Not enough memory for annotate.disassemblers\n"); - return -1; -} - int symbol__disassemble(struct symbol *sym, struct annotate_args *args) { struct annotation_options *options = args->options; @@ -2274,7 +2224,6 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) char symfs_filename[PATH_MAX]; bool delete_extract = false; struct kcore_extract kce; - const char *disassembler; bool decomp = false; int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename)); @@ -2334,28 +2283,26 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args) } } - err = annotation_options__init_disassemblers(options); - if (err) - goto out_remove_tmp; - err = -1; + for (u8 i = 0; i < ARRAY_SIZE(options->disassemblers) && err != 0; i++) { + enum perf_disassembler dis = options->disassemblers[i]; - for (int i = 0; i < options->nr_disassemblers && err != 0; ++i) { - disassembler = options->disassemblers[i]; - - if (!strcmp(disassembler, "llvm")) + switch (dis) { + case PERF_DISASM_LLVM: err = symbol__disassemble_llvm(symfs_filename, sym, args); - else if (!strcmp(disassembler, "capstone")) + break; + case PERF_DISASM_CAPSTONE: err = symbol__disassemble_capstone(symfs_filename, sym, args); - else if (!strcmp(disassembler, "objdump")) + break; + case PERF_DISASM_OBJDUMP: err = symbol__disassemble_objdump(symfs_filename, sym, args); - else - pr_debug("Unknown disassembler %s, skipping...\n", disassembler); - } - - if (err == 0) { - pr_debug("Disassembled with %s\nannotate.disassemblers=%s\n", - disassembler, options->disassemblers_str); + break; + case PERF_DISASM_UNKNOWN: /* End of disassemblers. */ + default: + goto out_remove_tmp; + } + if (err == 0) + pr_debug("Disassembled with %s\n", perf_disassembler__strs[dis]); } out_remove_tmp: if (decomp) diff --git a/tools/power/x86/turbostat/turbostat.8 b/tools/power/x86/turbostat/turbostat.8 index a7f7ed01421c..99bf905ade81 100644 --- a/tools/power/x86/turbostat/turbostat.8 +++ b/tools/power/x86/turbostat/turbostat.8 @@ -136,7 +136,7 @@ displays the statistics gathered since it was forked. The system configuration dump (if --quiet is not used) is followed by statistics. The first row of the statistics labels the content of each column (below). The second row of statistics is the system summary line. The system summary line has a '-' in the columns for the Package, Core, and CPU. The contents of the system summary line depends on the type of column. Columns that count items (eg. IRQ) show the sum across all CPUs in the system. Columns that show a percentage show the average across all CPUs in the system. Columns that dump raw MSR values simply show 0 in the summary. After the system summary row, each row describes a specific Package/Core/CPU. Note that if the --cpu parameter is used to limit which specific CPUs are displayed, turbostat will still collect statistics for all CPUs in the system and will still show the system summary for all CPUs in the system. .SH COLUMN DESCRIPTIONS .PP -\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any. This counter is disabled by default, and is enabled with "--enable usec", or --debug. On the summary row, usec refers to the total elapsed time to collect the counters on all cpus. +\fBusec\fP For each CPU, the number of microseconds elapsed during counter collection, including thread migration -- if any. This counter is disabled by default, and is enabled with "--enable usec", or --debug. On the summary row, usec refers to the total elapsed time to snapshot the procfs/sysfs and collect the counters on all cpus. .PP \fBTime_Of_Day_Seconds\fP For each CPU, the gettimeofday(2) value (seconds.subsec since Epoch) when the counters ending the measurement interval were collected. This column is disabled by default, and can be enabled with "--enable Time_Of_Day_Seconds" or "--debug". On the summary row, Time_Of_Day_Seconds refers to the timestamp following collection of counters on the last CPU. .PP @@ -190,7 +190,7 @@ The system configuration dump (if --quiet is not used) is followed by statistics .PP \fBRAMWatt\fP Watts consumed by the DRAM DIMMS -- available only on server processors. .PP -\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). Disabled by default. Enable with --enable SysWatt. +\fBSysWatt\fP Watts consumed by the whole platform (RAPL PSYS). .PP \fBPKG_%\fP percent of the interval that RAPL throttling was active on the Package. Note that the system summary is the sum of the package throttling time, and thus may be higher than 100% on a multi-package system. Note that the meaning of this field is model specific. For example, some hardware increments this counter when RAPL responds to thermal limits, but does not increment this counter when RAPL responds to power limits. Comparing PkgWatt and PkgTmp to system limits is necessary. .PP @@ -516,14 +516,40 @@ that they count at TSC rate, which is true on all processors tested to date. Volume 3B: System Programming Guide" https://www.intel.com/products/processor/manuals/ +.SH RUN THE LATEST VERSION +If turbostat complains that it doesn't recognize your processor, +please try the latest version. + +The latest version of turbostat does not require the latest version of the Linux kernel. +However, some features, such as perf(1) counters, do require kernel support. + +The latest turbostat release is available in the upstream Linux Kernel source tree. +eg. "git pull https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git" +and run make in tools/power/x86/turbostat/. + +n.b. "make install" will update your system manually, but a distro update may subsequently downgrade your turbostat to an older version. +For this reason, manually installing to /usr/local/bin may be what you want. + +Note that turbostat/Makefile has a "make snapshot" target, which will create a tar file +that can build without a local kernel source tree. + +If the upstream version isn't new enough, the development tree can be found here: +"git pull https://git.kernel.org/pub/scm/linux/kernel/git/lenb/linux.git turbostat" + +If the development tree doesn't work, please contact the author via chat, +or via email with the word "turbostat" on the Subject line. + .SH FILES .ta .nf +/sys/bus/event_source/devices/ /dev/cpu/*/msr +/sys/class/intel_pmt/ +/sys/devices/system/cpu/ .fi .SH "SEE ALSO" -msr(4), vmstat(8) +perf(1), msr(4), vmstat(8) .PP .SH AUTHOR .nf diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index 58a487c225a7..8d5011a0bf60 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -3,7 +3,7 @@ * turbostat -- show CPU frequency and C-state residency * on modern Intel and AMD processors. * - * Copyright (c) 2024 Intel Corporation. + * Copyright (c) 2025 Intel Corporation. * Len Brown <len.brown@intel.com> */ @@ -95,6 +95,8 @@ #define INTEL_ECORE_TYPE 0x20 #define INTEL_PCORE_TYPE 0x40 +#define ROUND_UP_TO_PAGE_SIZE(n) (((n) + 0x1000UL-1UL) & ~(0x1000UL-1UL)) + enum counter_scope { SCOPE_CPU, SCOPE_CORE, SCOPE_PACKAGE }; enum counter_type { COUNTER_ITEMS, COUNTER_CYCLES, COUNTER_SECONDS, COUNTER_USEC, COUNTER_K2M }; enum counter_format { FORMAT_RAW, FORMAT_DELTA, FORMAT_PERCENT, FORMAT_AVERAGE }; @@ -202,6 +204,8 @@ struct msr_counter bic[] = { { 0x0, "Die%c6", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "SysWatt", NULL, 0, 0, 0, NULL, 0 }, { 0x0, "Sys_J", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "NMI", NULL, 0, 0, 0, NULL, 0 }, + { 0x0, "CPU%c1e", NULL, 0, 0, 0, NULL, 0 }, }; #define MAX_BIC (sizeof(bic) / sizeof(struct msr_counter)) @@ -266,14 +270,16 @@ struct msr_counter bic[] = { #define BIC_Diec6 (1ULL << 58) #define BIC_SysWatt (1ULL << 59) #define BIC_Sys_J (1ULL << 60) +#define BIC_NMI (1ULL << 61) +#define BIC_CPU_c1e (1ULL << 62) -#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die ) -#define BIC_THERMAL_PWR ( BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__) +#define BIC_TOPOLOGY (BIC_Package | BIC_Node | BIC_CoreCnt | BIC_PkgCnt | BIC_Core | BIC_CPU | BIC_Die) +#define BIC_THERMAL_PWR (BIC_CoreTmp | BIC_PkgTmp | BIC_PkgWatt | BIC_CorWatt | BIC_GFXWatt | BIC_RAMWatt | BIC_PKG__ | BIC_RAM__ | BIC_SysWatt) #define BIC_FREQUENCY (BIC_Avg_MHz | BIC_Busy | BIC_Bzy_MHz | BIC_TSC_MHz | BIC_GFXMHz | BIC_GFXACTMHz | BIC_SAMMHz | BIC_SAMACTMHz | BIC_UNCORE_MHZ) -#define BIC_IDLE (BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) -#define BIC_OTHER ( BIC_IRQ | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) +#define BIC_IDLE (BIC_Busy | BIC_sysfs | BIC_CPU_c1 | BIC_CPU_c3 | BIC_CPU_c6 | BIC_CPU_c7 | BIC_GFX_rc6 | BIC_Pkgpc2 | BIC_Pkgpc3 | BIC_Pkgpc6 | BIC_Pkgpc7 | BIC_Pkgpc8 | BIC_Pkgpc9 | BIC_Pkgpc10 | BIC_CPU_LPI | BIC_SYS_LPI | BIC_Mod_c6 | BIC_Totl_c0 | BIC_Any_c0 | BIC_GFX_c0 | BIC_CPUGFX | BIC_SAM_mc6 | BIC_Diec6) +#define BIC_OTHER (BIC_IRQ | BIC_NMI | BIC_SMI | BIC_ThreadC | BIC_CoreTmp | BIC_IPC) -#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC | BIC_SysWatt | BIC_Sys_J) +#define BIC_DISABLED_BY_DEFAULT (BIC_USEC | BIC_TOD | BIC_APIC | BIC_X2APIC) unsigned long long bic_enabled = (0xFFFFFFFFFFFFFFFFULL & ~BIC_DISABLED_BY_DEFAULT); unsigned long long bic_present = BIC_USEC | BIC_TOD | BIC_sysfs | BIC_APIC | BIC_X2APIC; @@ -326,6 +332,7 @@ unsigned int rapl_joules; unsigned int summary_only; unsigned int list_header_only; unsigned int dump_only; +unsigned int force_load; unsigned int has_aperf; unsigned int has_aperf_access; unsigned int has_epb; @@ -353,7 +360,7 @@ unsigned long long cpuidle_cur_sys_lpi_us; unsigned int tj_max; unsigned int tj_max_override; double rapl_power_units, rapl_time_units; -double rapl_dram_energy_units, rapl_energy_units; +double rapl_dram_energy_units, rapl_energy_units, rapl_psys_energy_units; double rapl_joule_counter_range; unsigned int crystal_hz; unsigned long long tsc_hz; @@ -365,6 +372,9 @@ unsigned int has_hwp_activity_window; /* IA32_HWP_REQUEST[bits 41:32] */ unsigned int has_hwp_epp; /* IA32_HWP_REQUEST[bits 31:24] */ unsigned int has_hwp_pkg; /* IA32_HWP_REQUEST_PKG */ unsigned int first_counter_read = 1; + +static struct timeval procsysfs_tv_begin; + int ignore_stdin; bool no_msr; bool no_perf; @@ -419,6 +429,7 @@ struct platform_features { bool has_per_core_rapl; /* Indicates cores energy collection is per-core, not per-package. AMD specific for now */ bool has_rapl_divisor; /* Divisor for Energy unit raw value from MSR_RAPL_POWER_UNIT */ bool has_fixed_rapl_unit; /* Fixed Energy Unit used for DRAM RAPL Domain */ + bool has_fixed_rapl_psys_unit; /* Fixed Energy Unit used for PSYS RAPL Domain */ int rapl_quirk_tdp; /* Hardcoded TDP value when cannot be retrieved from hardware */ int tcc_offset_bits; /* TCC Offset bits in MSR_IA32_TEMPERATURE_TARGET */ bool enable_tsc_tweak; /* Use CPU Base freq instead of TSC freq for aperf/mperf counter */ @@ -819,6 +830,7 @@ static const struct platform_features spr_features = { .has_msr_core_c1_res = 1, .has_irtl_msrs = 1, .has_cst_prewake_bit = 1, + .has_fixed_rapl_psys_unit = 1, .trl_msrs = TRL_BASE | TRL_CORECOUNT, .rapl_msrs = RAPL_PKG_ALL | RAPL_DRAM_ALL | RAPL_PSYS, }; @@ -1024,6 +1036,7 @@ static const struct platform_data turbostat_pdata[] = { { INTEL_ARROWLAKE_U, &adl_features }, { INTEL_ARROWLAKE, &adl_features }, { INTEL_LUNARLAKE_M, &lnl_features }, + { INTEL_PANTHERLAKE_L, &lnl_features }, { INTEL_ATOM_SILVERMONT, &slv_features }, { INTEL_ATOM_SILVERMONT_D, &slvd_features }, { INTEL_ATOM_AIRMONT, &amt_features }, @@ -1036,6 +1049,7 @@ static const struct platform_data turbostat_pdata[] = { { INTEL_ATOM_GRACEMONT, &adl_features }, { INTEL_ATOM_CRESTMONT_X, &srf_features }, { INTEL_ATOM_CRESTMONT, &grr_features }, + { INTEL_ATOM_DARKMONT_X, &srf_features }, { INTEL_XEON_PHI_KNL, &knl_features }, { INTEL_XEON_PHI_KNM, &knl_features }, /* @@ -1054,9 +1068,10 @@ void probe_platform_features(unsigned int family, unsigned int model) { int i; - platform = &default_features; if (authentic_amd || hygon_genuine) { + /* fallback to default features on unsupported models */ + force_load++; if (max_extended_level >= 0x80000007) { unsigned int eax, ebx, ecx, edx; @@ -1065,11 +1080,11 @@ void probe_platform_features(unsigned int family, unsigned int model) if ((edx & (1 << 14)) && family >= 0x17) platform = &amd_features_with_rapl; } - return; + goto end; } if (!genuine_intel) - return; + goto end; for (i = 0; turbostat_pdata[i].features; i++) { if (VFM_FAMILY(turbostat_pdata[i].vfm) == family && VFM_MODEL(turbostat_pdata[i].vfm) == model) { @@ -1077,6 +1092,19 @@ void probe_platform_features(unsigned int family, unsigned int model) return; } } + +end: + if (force_load && !platform) { + fprintf(outf, "Forced to run on unsupported platform!\n"); + platform = &default_features; + } + + if (platform) + return; + + fprintf(stderr, "Unsupported platform detected.\n" + "\tSee RUN THE LATEST VERSION on turbostat(8)\n"); + exit(1); } /* Model specific support End */ @@ -1094,8 +1122,8 @@ int backwards_count; char *progname; #define CPU_SUBSET_MAXCPUS 1024 /* need to use before probe... */ -cpu_set_t *cpu_present_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset; -size_t cpu_present_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size; +cpu_set_t *cpu_present_set, *cpu_possible_set, *cpu_effective_set, *cpu_allowed_set, *cpu_affinity_set, *cpu_subset; +size_t cpu_present_setsize, cpu_possible_setsize, cpu_effective_setsize, cpu_allowed_setsize, cpu_affinity_setsize, cpu_subset_size; #define MAX_ADDED_THREAD_COUNTERS 24 #define MAX_ADDED_CORE_COUNTERS 8 #define MAX_ADDED_PACKAGE_COUNTERS 16 @@ -1271,7 +1299,7 @@ static const struct rapl_counter_arch_info rapl_counter_arch_infos[] = { .msr = MSR_PLATFORM_ENERGY_STATUS, .msr_mask = 0x00000000FFFFFFFF, .msr_shift = 0, - .platform_rapl_msr_scale = &rapl_energy_units, + .platform_rapl_msr_scale = &rapl_psys_energy_units, .rci_index = RAPL_RCI_INDEX_ENERGY_PLATFORM, .bic = BIC_SysWatt | BIC_Sys_J, .compat_scale = 1.0, @@ -1510,6 +1538,17 @@ static struct msr_counter_arch_info msr_counter_arch_infos[] = { #define PMT_COUNTER_MTL_DC6_LSB 0 #define PMT_COUNTER_MTL_DC6_MSB 63 #define PMT_MTL_DC6_GUID 0x1a067102 +#define PMT_MTL_DC6_SEQ 0 + +#define PMT_COUNTER_CWF_MC1E_OFFSET_BASE 20936 +#define PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT 24 +#define PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE 12 +#define PMT_COUNTER_CWF_CPUS_PER_MODULE 4 +#define PMT_COUNTER_CWF_MC1E_LSB 0 +#define PMT_COUNTER_CWF_MC1E_MSB 63 +#define PMT_CWF_MC1E_GUID 0x14421519 + +unsigned long long tcore_clock_freq_hz = 800000000; #define PMT_COUNTER_NAME_SIZE_BYTES 16 #define PMT_COUNTER_TYPE_NAME_SIZE_BYTES 32 @@ -1533,6 +1572,7 @@ struct pmt_mmio { enum pmt_datatype { PMT_TYPE_RAW, PMT_TYPE_XTAL_TIME, + PMT_TYPE_TCORE_CLOCK, }; struct pmt_domain_info { @@ -1562,6 +1602,93 @@ struct pmt_counter { struct pmt_domain_info *domains; }; +/* + * PMT telemetry directory iterator. + * Used to iterate telemetry files in sysfs in correct order. + */ +struct pmt_diriter_t { + DIR *dir; + struct dirent **namelist; + unsigned int num_names; + unsigned int current_name_idx; +}; + +int pmt_telemdir_filter(const struct dirent *e) +{ + unsigned int dummy; + + return sscanf(e->d_name, "telem%u", &dummy); +} + +int pmt_telemdir_sort(const struct dirent **a, const struct dirent **b) +{ + unsigned int aidx = 0, bidx = 0; + + sscanf((*a)->d_name, "telem%u", &aidx); + sscanf((*b)->d_name, "telem%u", &bidx); + + return aidx >= bidx; +} + +const struct dirent *pmt_diriter_next(struct pmt_diriter_t *iter) +{ + const struct dirent *ret = NULL; + + if (!iter->dir) + return NULL; + + if (iter->current_name_idx >= iter->num_names) + return NULL; + + ret = iter->namelist[iter->current_name_idx]; + ++iter->current_name_idx; + + return ret; +} + +const struct dirent *pmt_diriter_begin(struct pmt_diriter_t *iter, const char *pmt_root_path) +{ + int num_names = iter->num_names; + + if (!iter->dir) { + iter->dir = opendir(pmt_root_path); + if (iter->dir == NULL) + return NULL; + + num_names = scandir(pmt_root_path, &iter->namelist, pmt_telemdir_filter, pmt_telemdir_sort); + if (num_names == -1) + return NULL; + } + + iter->current_name_idx = 0; + iter->num_names = num_names; + + return pmt_diriter_next(iter); +} + +void pmt_diriter_init(struct pmt_diriter_t *iter) +{ + memset(iter, 0, sizeof(*iter)); +} + +void pmt_diriter_remove(struct pmt_diriter_t *iter) +{ + if (iter->namelist) { + for (unsigned int i = 0; i < iter->num_names; i++) { + free(iter->namelist[i]); + iter->namelist[i] = NULL; + } + } + + free(iter->namelist); + iter->namelist = NULL; + iter->num_names = 0; + iter->current_name_idx = 0; + + closedir(iter->dir); + iter->dir = NULL; +} + unsigned int pmt_counter_get_width(const struct pmt_counter *p) { return (p->msb - p->lsb) + 1; @@ -1611,6 +1738,7 @@ struct thread_data { unsigned long long c1; unsigned long long instr_count; unsigned long long irq_count; + unsigned long long nmi_count; unsigned int smi_count; unsigned int cpu_id; unsigned int apic_id; @@ -1917,6 +2045,7 @@ struct timeval tv_even, tv_odd, tv_delta; int *irq_column_2_cpu; /* /proc/interrupts column numbers */ int *irqs_per_cpu; /* indexed by cpu_num */ +int *nmi_per_cpu; /* indexed by cpu_num */ void setup_all_buffers(bool startup); @@ -1944,6 +2073,8 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk { int retval, pkg_no, core_no, thread_no, node_no; + retval = 0; + for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { for (node_no = 0; node_no < topo.nodes_per_pkg; node_no++) { for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { @@ -1959,14 +2090,12 @@ int for_all_cpus(int (func) (struct thread_data *, struct core_data *, struct pk c = GET_CORE(core_base, core_no, node_no, pkg_no); p = GET_PKG(pkg_base, pkg_no); - retval = func(t, c, p); - if (retval) - return retval; + retval |= func(t, c, p); } } } } - return 0; + return retval; } int is_cpu_first_thread_in_core(struct thread_data *t, struct core_data *c, struct pkg_data *p) @@ -2085,13 +2214,17 @@ int get_msr(int cpu, off_t offset, unsigned long long *msr) int probe_msr(int cpu, off_t offset) { ssize_t retval; - unsigned long long dummy; + unsigned long long value; assert(!no_msr); - retval = pread(get_msr_fd(cpu), &dummy, sizeof(dummy), offset); + retval = pread(get_msr_fd(cpu), &value, sizeof(value), offset); - if (retval != sizeof(dummy)) + /* + * Expect MSRs to accumulate some non-zero value since the system was powered on. + * Treat zero as a read failure. + */ + if (retval != sizeof(value) || value == 0) return 1; return 0; @@ -2135,41 +2268,54 @@ void help(void) "when COMMAND completes.\n" "If no COMMAND is specified, turbostat wakes every 5-seconds\n" "to print statistics, until interrupted.\n" - " -a, --add add a counter\n" + " -a, --add counter\n" + " add a counter\n" " eg. --add msr0x10,u64,cpu,delta,MY_TSC\n" " eg. --add perf/cstate_pkg/c2-residency,package,delta,percent,perfPC2\n" " eg. --add pmt,name=XTAL,type=raw,domain=package0,offset=0,lsb=0,msb=63,guid=0x1a067102\n" - " -c, --cpu cpu-set limit output to summary plus cpu-set:\n" + " -c, --cpu cpu-set\n" + " limit output to summary plus cpu-set:\n" " {core | package | j,k,l..m,n-p }\n" - " -d, --debug displays usec, Time_Of_Day_Seconds and more debugging\n" + " -d, --debug\n" + " displays usec, Time_Of_Day_Seconds and more debugging\n" " debug messages are printed to stderr\n" - " -D, --Dump displays the raw counter values\n" - " -e, --enable [all | column]\n" + " -D, --Dump\n" + " displays the raw counter values\n" + " -e, --enable [all | column]\n" " shows all or the specified disabled column\n" - " -H, --hide [column|column,column,...]\n" + " -f, --force\n" + " force load turbostat with minimum default features on unsupported platforms.\n" + " -H, --hide [column | column,column,...]\n" " hide the specified column(s)\n" " -i, --interval sec.subsec\n" - " Override default 5-second measurement interval\n" - " -J, --Joules displays energy in Joules instead of Watts\n" - " -l, --list list column headers only\n" - " -M, --no-msr Disable all uses of the MSR driver\n" - " -P, --no-perf Disable all uses of the perf API\n" + " override default 5-second measurement interval\n" + " -J, --Joules\n" + " displays energy in Joules instead of Watts\n" + " -l, --list\n" + " list column headers only\n" + " -M, --no-msr\n" + " disable all uses of the MSR driver\n" + " -P, --no-perf\n" + " disable all uses of the perf API\n" " -n, --num_iterations num\n" " number of the measurement iterations\n" " -N, --header_iterations num\n" " print header every num iterations\n" " -o, --out file\n" " create or truncate \"file\" for all output\n" - " -q, --quiet skip decoding system configuration header\n" - " -s, --show [column|column,column,...]\n" + " -q, --quiet\n" + " skip decoding system configuration header\n" + " -s, --show [column | column,column,...]\n" " show only the specified column(s)\n" " -S, --Summary\n" " limits output to 1-line system summary per interval\n" " -T, --TCC temperature\n" " sets the Thermal Control Circuit temperature in\n" " degrees Celsius\n" - " -h, --help print this help message\n" - " -v, --version print version information\n" "\n" "For more help, run \"man turbostat\"\n"); + " -h, --help\n" + " print this help message\n" + " -v, --version\n" + " print version information\n\nFor more help, run \"man turbostat\"\n"); } /* @@ -2289,6 +2435,12 @@ void print_header(char *delim) else outp += sprintf(outp, "%sIRQ", (printed++ ? delim : "")); } + if (DO_BIC(BIC_NMI)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s NMI", (printed++ ? delim : "")); + else + outp += sprintf(outp, "%sNMI", (printed++ ? delim : "")); + } if (DO_BIC(BIC_SMI)) outp += sprintf(outp, "%sSMI", (printed++ ? delim : "")); @@ -2335,6 +2487,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: + case PMT_TYPE_TCORE_CLOCK: outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2409,6 +2562,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: + case PMT_TYPE_TCORE_CLOCK: outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2540,6 +2694,7 @@ void print_header(char *delim) break; case PMT_TYPE_XTAL_TIME: + case PMT_TYPE_TCORE_CLOCK: outp += sprintf(outp, "%s%s", (printed++ ? delim : ""), ppmt->name); break; } @@ -2575,6 +2730,8 @@ int dump_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p if (DO_BIC(BIC_IRQ)) outp += sprintf(outp, "IRQ: %lld\n", t->irq_count); + if (DO_BIC(BIC_NMI)) + outp += sprintf(outp, "IRQ: %lld\n", t->nmi_count); if (DO_BIC(BIC_SMI)) outp += sprintf(outp, "SMI: %d\n", t->smi_count); @@ -2794,6 +2951,14 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->irq_count); } + /* NMI */ + if (DO_BIC(BIC_NMI)) { + if (sums_need_wide_columns) + outp += sprintf(outp, "%s%8lld", (printed++ ? delim : ""), t->nmi_count); + else + outp += sprintf(outp, "%s%lld", (printed++ ? delim : ""), t->nmi_count); + } + /* SMI */ if (DO_BIC(BIC_SMI)) outp += sprintf(outp, "%s%d", (printed++ ? delim : ""), t->smi_count); @@ -2848,7 +3013,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, ppmt = sys.pmt_tp; ppmt; i++, ppmt = ppmt->next) { const unsigned long value_raw = t->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + double value_converted; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2860,8 +3025,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: + value_converted = 100.0 * value_raw / crystal_hz / interval_float; outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; + + case PMT_TYPE_TCORE_CLOCK: + value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float; + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); } } @@ -2928,7 +3098,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, ppmt = sys.pmt_cp; ppmt; i++, ppmt = ppmt->next) { const unsigned long value_raw = c->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + double value_converted; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -2940,8 +3110,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: + value_converted = 100.0 * value_raw / crystal_hz / interval_float; outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; + + case PMT_TYPE_TCORE_CLOCK: + value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float; + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); } } @@ -3126,7 +3301,7 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data for (i = 0, ppmt = sys.pmt_pp; ppmt; i++, ppmt = ppmt->next) { const unsigned long value_raw = p->pmt_counter[i]; - const double value_converted = 100.0 * value_raw / crystal_hz / interval_float; + double value_converted; switch (ppmt->type) { case PMT_TYPE_RAW: if (pmt_counter_get_width(ppmt) <= 32) @@ -3138,8 +3313,13 @@ int format_counters(struct thread_data *t, struct core_data *c, struct pkg_data break; case PMT_TYPE_XTAL_TIME: + value_converted = 100.0 * value_raw / crystal_hz / interval_float; outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); break; + + case PMT_TYPE_TCORE_CLOCK: + value_converted = 100.0 * value_raw / tcore_clock_freq_hz / interval_float; + outp += sprintf(outp, "%s%.2f", (printed++ ? delim : ""), value_converted); } } @@ -3409,6 +3589,9 @@ int delta_thread(struct thread_data *new, struct thread_data *old, struct core_d if (DO_BIC(BIC_IRQ)) old->irq_count = new->irq_count - old->irq_count; + if (DO_BIC(BIC_NMI)) + old->nmi_count = new->nmi_count - old->nmi_count; + if (DO_BIC(BIC_SMI)) old->smi_count = new->smi_count - old->smi_count; @@ -3447,12 +3630,10 @@ int delta_cpu(struct thread_data *t, struct core_data *c, /* always calculate thread delta */ retval = delta_thread(t, t2, c2); /* c2 is core delta */ - if (retval) - return retval; /* calculate package delta only for 1st core in package */ if (is_cpu_first_core_in_package(t, c, p)) - retval = delta_package(p, p2); + retval |= delta_package(p, p2); return retval; } @@ -3489,6 +3670,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data t->instr_count = 0; t->irq_count = 0; + t->nmi_count = 0; t->smi_count = 0; c->c3 = 0; @@ -3580,7 +3762,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) /* remember first tv_begin */ if (average.threads.tv_begin.tv_sec == 0) - average.threads.tv_begin = t->tv_begin; + average.threads.tv_begin = procsysfs_tv_begin; /* remember last tv_end */ average.threads.tv_end = t->tv_end; @@ -3593,6 +3775,7 @@ int sum_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) average.threads.instr_count += t->instr_count; average.threads.irq_count += t->irq_count; + average.threads.nmi_count += t->nmi_count; average.threads.smi_count += t->smi_count; for (i = 0, mp = sys.tp; mp; i++, mp = mp->next) { @@ -3734,6 +3917,9 @@ void compute_average(struct thread_data *t, struct core_data *c, struct pkg_data if (average.threads.irq_count > 9999999) sums_need_wide_columns = 1; + if (average.threads.nmi_count > 9999999) + sums_need_wide_columns = 1; + average.cores.c3 /= topo.allowed_cores; average.cores.c6 /= topo.allowed_cores; @@ -4546,7 +4732,8 @@ unsigned long pmt_gen_value_mask(unsigned int lsb, unsigned int msb) unsigned long pmt_read_counter(struct pmt_counter *ppmt, unsigned int domain_id) { - assert(domain_id < ppmt->num_domains); + if (domain_id >= ppmt->num_domains) + return 0; const unsigned long *pmmio = ppmt->domains[domain_id].pcounter; const unsigned long value = pmmio ? *pmmio : 0; @@ -4590,6 +4777,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (DO_BIC(BIC_IRQ)) t->irq_count = irqs_per_cpu[cpu]; + if (DO_BIC(BIC_NMI)) + t->nmi_count = nmi_per_cpu[cpu]; get_cstate_counters(cpu, t, c, p); @@ -5335,6 +5524,7 @@ void free_all_buffers(void) free(irq_column_2_cpu); free(irqs_per_cpu); + free(nmi_per_cpu); for (i = 0; i <= topo.max_cpu_num; ++i) { if (cpus[i].put_ids) @@ -5566,6 +5756,8 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, { int retval, pkg_no, node_no, core_no, thread_no; + retval = 0; + for (pkg_no = 0; pkg_no < topo.num_packages; ++pkg_no) { for (node_no = 0; node_no < topo.nodes_per_pkg; ++node_no) { for (core_no = 0; core_no < topo.cores_per_node; ++core_no) { @@ -5587,14 +5779,12 @@ int for_all_cpus_2(int (func) (struct thread_data *, struct core_data *, p = GET_PKG(pkg_base, pkg_no); p2 = GET_PKG(pkg_base2, pkg_no); - retval = func(t, c, p, t2, c2, p2); - if (retval) - return retval; + retval |= func(t, c, p, t2, c2, p2); } } } } - return 0; + return retval; } /* @@ -5791,31 +5981,37 @@ int snapshot_proc_interrupts(void) irq_column_2_cpu[column] = cpu_number; irqs_per_cpu[cpu_number] = 0; + nmi_per_cpu[cpu_number] = 0; } /* read /proc/interrupt count lines and sum up irqs per cpu */ while (1) { int column; char buf[64]; + int this_row_is_nmi = 0; - retval = fscanf(fp, " %s:", buf); /* flush irq# "N:" */ + retval = fscanf(fp, " %s:", buf); /* irq# "N:" */ if (retval != 1) break; + if (strncmp(buf, "NMI", strlen("NMI")) == 0) + this_row_is_nmi = 1; + /* read the count per cpu */ for (column = 0; column < topo.num_cpus; ++column) { int cpu_number, irq_count; retval = fscanf(fp, " %d", &irq_count); + if (retval != 1) break; cpu_number = irq_column_2_cpu[column]; irqs_per_cpu[cpu_number] += irq_count; - + if (this_row_is_nmi) + nmi_per_cpu[cpu_number] += irq_count; } - while (getc(fp) != '\n') ; /* flush interrupt description */ } @@ -5912,7 +6108,9 @@ int snapshot_sys_lpi_us(void) */ int snapshot_proc_sysfs_files(void) { - if (DO_BIC(BIC_IRQ)) + gettimeofday(&procsysfs_tv_begin, (struct timezone *)NULL); + + if (DO_BIC(BIC_IRQ) || DO_BIC(BIC_NMI)) if (snapshot_proc_interrupts()) return 1; @@ -7043,6 +7241,11 @@ void rapl_probe_intel(void) else rapl_dram_energy_units = rapl_energy_units; + if (platform->has_fixed_rapl_psys_unit) + rapl_psys_energy_units = 1.0; + else + rapl_psys_energy_units = rapl_energy_units; + time_unit = msr >> 16 & 0xF; if (time_unit == 0) time_unit = 0xA; @@ -8233,6 +8436,7 @@ void process_cpuid() aperf_mperf_multiplier = platform->need_perf_multiplier ? 1024 : 1; BIC_PRESENT(BIC_IRQ); + BIC_PRESENT(BIC_NMI); BIC_PRESENT(BIC_TSC_MHz); } @@ -8292,6 +8496,33 @@ int dir_filter(const struct dirent *dirp) return 0; } +char *possible_file = "/sys/devices/system/cpu/possible"; +char possible_buf[1024]; + +int initialize_cpu_possible_set(void) +{ + FILE *fp; + + fp = fopen(possible_file, "r"); + if (!fp) { + warn("open %s", possible_file); + return -1; + } + if (fread(possible_buf, sizeof(char), 1024, fp) == 0) { + warn("read %s", possible_file); + goto err; + } + if (parse_cpu_str(possible_buf, cpu_possible_set, cpu_possible_setsize)) { + warnx("%s: cpu str malformat %s\n", possible_file, cpu_effective_str); + goto err; + } + return 0; + +err: + fclose(fp); + return -1; +} + void topology_probe(bool startup) { int i; @@ -8324,6 +8555,16 @@ void topology_probe(bool startup) for_all_proc_cpus(mark_cpu_present); /* + * Allocate and initialize cpu_possible_set + */ + cpu_possible_set = CPU_ALLOC((topo.max_cpu_num + 1)); + if (cpu_possible_set == NULL) + err(3, "CPU_ALLOC"); + cpu_possible_setsize = CPU_ALLOC_SIZE((topo.max_cpu_num + 1)); + CPU_ZERO_S(cpu_possible_setsize, cpu_possible_set); + initialize_cpu_possible_set(); + + /* * Allocate and initialize cpu_effective_set */ cpu_effective_set = CPU_ALLOC((topo.max_cpu_num + 1)); @@ -8583,7 +8824,11 @@ void allocate_irq_buffers(void) irqs_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int)); if (irqs_per_cpu == NULL) - err(-1, "calloc %d", topo.max_cpu_num + 1); + err(-1, "calloc %d IRQ", topo.max_cpu_num + 1); + + nmi_per_cpu = calloc(topo.max_cpu_num + 1, sizeof(int)); + if (nmi_per_cpu == NULL) + err(-1, "calloc %d NMI", topo.max_cpu_num + 1); } int update_topo(struct thread_data *t, struct core_data *c, struct pkg_data *p) @@ -8854,49 +9099,36 @@ int parse_telem_info_file(int fd_dir, const char *info_filename, const char *for struct pmt_mmio *pmt_mmio_open(unsigned int target_guid) { - DIR *dirp; - struct dirent *entry; + struct pmt_diriter_t pmt_iter; + const struct dirent *entry; struct stat st; - unsigned int telem_idx; int fd_telem_dir, fd_pmt; unsigned long guid, size, offset; size_t mmap_size; void *mmio; - struct pmt_mmio *ret = NULL; + struct pmt_mmio *head = NULL, *last = NULL; + struct pmt_mmio *new_pmt = NULL; if (stat(SYSFS_TELEM_PATH, &st) == -1) return NULL; - dirp = opendir(SYSFS_TELEM_PATH); - if (dirp == NULL) + pmt_diriter_init(&pmt_iter); + entry = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH); + if (!entry) { + pmt_diriter_remove(&pmt_iter); return NULL; + } - for (;;) { - entry = readdir(dirp); - - if (entry == NULL) - break; - - if (strcmp(entry->d_name, ".") == 0) - continue; - - if (strcmp(entry->d_name, "..") == 0) - continue; - - if (sscanf(entry->d_name, "telem%u", &telem_idx) != 1) - continue; - - if (fstatat(dirfd(dirp), entry->d_name, &st, 0) == -1) { + for ( ; entry != NULL; entry = pmt_diriter_next(&pmt_iter)) { + if (fstatat(dirfd(pmt_iter.dir), entry->d_name, &st, 0) == -1) break; - } if (!S_ISDIR(st.st_mode)) continue; - fd_telem_dir = openat(dirfd(dirp), entry->d_name, O_RDONLY); - if (fd_telem_dir == -1) { + fd_telem_dir = openat(dirfd(pmt_iter.dir), entry->d_name, O_RDONLY); + if (fd_telem_dir == -1) break; - } if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) { close(fd_telem_dir); @@ -8924,38 +9156,54 @@ struct pmt_mmio *pmt_mmio_open(unsigned int target_guid) if (fd_pmt == -1) goto loop_cleanup_and_break; - mmap_size = (size + 0x1000UL) & (~0x1000UL); + mmap_size = ROUND_UP_TO_PAGE_SIZE(size); mmio = mmap(0, mmap_size, PROT_READ, MAP_SHARED, fd_pmt, 0); if (mmio != MAP_FAILED) { - if (debug) fprintf(stderr, "%s: 0x%lx mmaped at: %p\n", __func__, guid, mmio); - ret = calloc(1, sizeof(*ret)); + new_pmt = calloc(1, sizeof(*new_pmt)); - if (!ret) { + if (!new_pmt) { fprintf(stderr, "%s: Failed to allocate pmt_mmio\n", __func__); exit(1); } - ret->guid = guid; - ret->mmio_base = mmio; - ret->pmt_offset = offset; - ret->size = size; + /* + * Create linked list of mmaped regions, + * but preserve the ordering from sysfs. + * Ordering is important for the user to + * use the seq=%u parameter when adding a counter. + */ + new_pmt->guid = guid; + new_pmt->mmio_base = mmio; + new_pmt->pmt_offset = offset; + new_pmt->size = size; + new_pmt->next = pmt_mmios; + + if (last) + last->next = new_pmt; + else + head = new_pmt; - ret->next = pmt_mmios; - pmt_mmios = ret; + last = new_pmt; } loop_cleanup_and_break: close(fd_pmt); close(fd_telem_dir); - break; } - closedir(dirp); + pmt_diriter_remove(&pmt_iter); - return ret; + /* + * If we found something, stick just + * created linked list to the front. + */ + if (head) + pmt_mmios = head; + + return head; } struct pmt_mmio *pmt_mmio_find(unsigned int guid) @@ -8992,7 +9240,7 @@ void *pmt_get_counter_pointer(struct pmt_mmio *pmmio, unsigned long counter_offs return ret; } -struct pmt_mmio *pmt_add_guid(unsigned int guid) +struct pmt_mmio *pmt_add_guid(unsigned int guid, unsigned int seq) { struct pmt_mmio *ret; @@ -9000,6 +9248,11 @@ struct pmt_mmio *pmt_add_guid(unsigned int guid) if (!ret) ret = pmt_mmio_open(guid); + while (ret && seq) { + ret = ret->next; + --seq; + } + return ret; } @@ -9046,7 +9299,7 @@ void pmt_counter_add_domain(struct pmt_counter *pcounter, unsigned long *pmmio, pcounter->domains[domain_id].pcounter = pmmio; } -int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, +int pmt_add_counter(unsigned int guid, unsigned int seq, const char *name, enum pmt_datatype type, unsigned int lsb, unsigned int msb, unsigned int offset, enum counter_scope scope, enum counter_format format, unsigned int domain_id, enum pmt_open_mode mode) { @@ -9066,10 +9319,10 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, exit(1); } - mmio = pmt_add_guid(guid); + mmio = pmt_add_guid(guid, seq); if (!mmio) { if (mode != PMT_OPEN_TRY) { - fprintf(stderr, "%s: failed to map PMT MMIO for guid %x\n", __func__, guid); + fprintf(stderr, "%s: failed to map PMT MMIO for guid %x, seq %u\n", __func__, guid, seq); exit(1); } @@ -9124,10 +9377,68 @@ int pmt_add_counter(unsigned int guid, const char *name, enum pmt_datatype type, void pmt_init(void) { + int cpu_num; + unsigned long seq, offset, mod_num; + if (BIC_IS_ENABLED(BIC_Diec6)) { - pmt_add_counter(PMT_MTL_DC6_GUID, "Die%c6", PMT_TYPE_XTAL_TIME, PMT_COUNTER_MTL_DC6_LSB, - PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, SCOPE_PACKAGE, FORMAT_DELTA, - 0, PMT_OPEN_TRY); + pmt_add_counter(PMT_MTL_DC6_GUID, PMT_MTL_DC6_SEQ, "Die%c6", PMT_TYPE_XTAL_TIME, + PMT_COUNTER_MTL_DC6_LSB, PMT_COUNTER_MTL_DC6_MSB, PMT_COUNTER_MTL_DC6_OFFSET, + SCOPE_PACKAGE, FORMAT_DELTA, 0, PMT_OPEN_TRY); + } + + if (BIC_IS_ENABLED(BIC_CPU_c1e)) { + seq = 0; + offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE; + mod_num = 0; /* Relative module number for current PMT file. */ + + /* Open the counter for each CPU. */ + for (cpu_num = 0; cpu_num < topo.max_cpu_num;) { + + if (cpu_is_not_allowed(cpu_num)) + goto next_loop_iter; + + /* + * Set the scope to CPU, even though CWF report the counter per module. + * CPUs inside the same module will read from the same location, instead of reporting zeros. + * + * CWF with newer firmware might require a PMT_TYPE_XTAL_TIME intead of PMT_TYPE_TCORE_CLOCK. + */ + pmt_add_counter(PMT_CWF_MC1E_GUID, seq, "CPU%c1e", PMT_TYPE_TCORE_CLOCK, + PMT_COUNTER_CWF_MC1E_LSB, PMT_COUNTER_CWF_MC1E_MSB, offset, SCOPE_CPU, + FORMAT_DELTA, cpu_num, PMT_OPEN_TRY); + + /* + * Rather complex logic for each time we go to the next loop iteration, + * so keep it as a label. + */ +next_loop_iter: + /* + * Advance the cpu number and check if we should also advance offset to + * the next counter inside the PMT file. + * + * On Clearwater Forest platform, the counter is reported per module, + * so open the same counter for all of the CPUs inside the module. + * That way, reported table show the correct value for all of the CPUs inside the module, + * instead of zeros. + */ + ++cpu_num; + if (cpu_num % PMT_COUNTER_CWF_CPUS_PER_MODULE == 0) { + offset += PMT_COUNTER_CWF_MC1E_OFFSET_INCREMENT; + ++mod_num; + } + + /* + * There are PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE in each PMT file. + * + * If that number is reached, seq must be incremented to advance to the next file in a sequence. + * Offset inside that file and a module counter has to be reset. + */ + if (mod_num == PMT_COUNTER_CWF_MC1E_NUM_MODULES_PER_FILE) { + ++seq; + offset = PMT_COUNTER_CWF_MC1E_OFFSET_BASE; + mod_num = 0; + } + } } } @@ -9163,6 +9474,18 @@ void turbostat_init() } } +void affinitize_child(void) +{ + /* Prefer cpu_possible_set, if available */ + if (sched_setaffinity(0, cpu_possible_setsize, cpu_possible_set)) { + warn("sched_setaffinity cpu_possible_set"); + + /* Otherwise, allow child to run on same cpu set as turbostat */ + if (sched_setaffinity(0, cpu_allowed_setsize, cpu_allowed_set)) + warn("sched_setaffinity cpu_allowed_set"); + } +} + int fork_it(char **argv) { pid_t child_pid; @@ -9178,6 +9501,7 @@ int fork_it(char **argv) child_pid = fork(); if (!child_pid) { /* child */ + affinitize_child(); execvp(argv[0], argv); err(errno, "exec %s", argv[0]); } else { @@ -9204,10 +9528,9 @@ int fork_it(char **argv) timersub(&tv_odd, &tv_even, &tv_delta); if (for_all_cpus_2(delta_cpu, ODD_COUNTERS, EVEN_COUNTERS)) fprintf(outf, "%s: Counter reset detected\n", progname); - else { - compute_average(EVEN_COUNTERS); - format_all_counters(EVEN_COUNTERS); - } + + compute_average(EVEN_COUNTERS); + format_all_counters(EVEN_COUNTERS); fprintf(outf, "%.6f sec\n", tv_delta.tv_sec + tv_delta.tv_usec / 1000000.0); @@ -9236,7 +9559,7 @@ int get_and_dump_counters(void) void print_version() { - fprintf(outf, "turbostat version 2024.11.30 - Len Brown <lenb@kernel.org>\n"); + fprintf(outf, "turbostat version 2025.02.02 - Len Brown <lenb@kernel.org>\n"); } #define COMMAND_LINE_SIZE 2048 @@ -9561,7 +9884,7 @@ next: } if ((msr_num == 0) && (path == NULL) && (perf_device[0] == '\0' || perf_event[0] == '\0')) { - fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event ) required\n"); + fprintf(stderr, "--add: (msrDDD | msr0xXXX | /path_to_counter | perf/device/event) required\n"); fail++; } @@ -9599,15 +9922,100 @@ bool starts_with(const char *str, const char *prefix) return strncmp(prefix, str, strlen(prefix)) == 0; } +int pmt_parse_from_path(const char *target_path, unsigned int *out_guid, unsigned int *out_seq) +{ + struct pmt_diriter_t pmt_iter; + const struct dirent *dirname; + struct stat stat, target_stat; + int fd_telem_dir = -1; + int fd_target_dir; + unsigned int seq = 0; + unsigned long guid, target_guid; + int ret = -1; + + fd_target_dir = open(target_path, O_RDONLY | O_DIRECTORY); + if (fd_target_dir == -1) { + return -1; + } + + if (fstat(fd_target_dir, &target_stat) == -1) { + fprintf(stderr, "%s: Failed to stat the target: %s", __func__, strerror(errno)); + exit(1); + } + + if (parse_telem_info_file(fd_target_dir, "guid", "%lx", &target_guid)) { + fprintf(stderr, "%s: Failed to parse the target guid file: %s", __func__, strerror(errno)); + exit(1); + } + + close(fd_target_dir); + + pmt_diriter_init(&pmt_iter); + + for (dirname = pmt_diriter_begin(&pmt_iter, SYSFS_TELEM_PATH); dirname != NULL; + dirname = pmt_diriter_next(&pmt_iter)) { + + fd_telem_dir = openat(dirfd(pmt_iter.dir), dirname->d_name, O_RDONLY | O_DIRECTORY); + if (fd_telem_dir == -1) + continue; + + if (parse_telem_info_file(fd_telem_dir, "guid", "%lx", &guid)) { + fprintf(stderr, "%s: Failed to parse the guid file: %s", __func__, strerror(errno)); + continue; + } + + if (fstat(fd_telem_dir, &stat) == -1) { + fprintf(stderr, "%s: Failed to stat %s directory: %s", __func__, + dirname->d_name, strerror(errno)); + continue; + } + + /* + * If reached the same directory as target, exit the loop. + * Seq has the correct value now. + */ + if (stat.st_dev == target_stat.st_dev && stat.st_ino == target_stat.st_ino) { + ret = 0; + break; + } + + /* + * If reached directory with the same guid, + * but it's not the target directory yet, + * increment seq and continue the search. + */ + if (guid == target_guid) + ++seq; + + close(fd_telem_dir); + fd_telem_dir = -1; + } + + pmt_diriter_remove(&pmt_iter); + + if (fd_telem_dir != -1) + close(fd_telem_dir); + + if (!ret) { + *out_guid = target_guid; + *out_seq = seq; + } + + return ret; +} + void parse_add_command_pmt(char *add_command) { char *name = NULL; char *type_name = NULL; char *format_name = NULL; + char *direct_path = NULL; + static const char direct_path_prefix[] = "path="; unsigned int offset; unsigned int lsb; unsigned int msb; unsigned int guid; + unsigned int seq = 0; /* By default, pick first file in a sequence with a given GUID. */ unsigned int domain_id; enum counter_scope scope = 0; enum pmt_datatype type = PMT_TYPE_RAW; @@ -9687,6 +10095,13 @@ void parse_add_command_pmt(char *add_command) goto next; } + if (sscanf(add_command, "seq=%x", &seq) == 1) + goto next; + + if (strncmp(add_command, direct_path_prefix, strlen(direct_path_prefix)) == 0) { + direct_path = add_command + strlen(direct_path_prefix); + goto next; + } next: add_command = strchr(add_command, ','); if (add_command) { @@ -9737,6 +10152,11 @@ next: has_type = true; } + if (strcmp("tcore_clock", type_name) == 0) { + type = PMT_TYPE_TCORE_CLOCK; + has_type = true; + } + if (!has_type) { printf("%s: invalid %s: %s\n", __func__, "type", type_name); exit(1); @@ -9758,8 +10178,24 @@ next: exit(1); } + if (direct_path && has_guid) { + printf("%s: path and guid+seq parameters are mutually exclusive\n" + "notice: passed guid=0x%x and path=%s\n", __func__, guid, direct_path); + exit(1); + } + + if (direct_path) { + if (pmt_parse_from_path(direct_path, &guid, &seq)) { + printf("%s: failed to parse PMT file from %s\n", __func__, direct_path); + exit(1); + } + + /* GUID was just infered from the direct path. */ + has_guid = true; + } + if (!has_guid) { - printf("%s: missing %s\n", __func__, "guid"); + printf("%s: missing %s\n", __func__, "guid or path"); exit(1); } @@ -9773,7 +10209,7 @@ next: exit(1); } - pmt_add_counter(guid, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED); + pmt_add_counter(guid, seq, name, type, lsb, msb, offset, scope, format, domain_id, PMT_OPEN_REQUIRED); } void parse_add_command(char *add_command) @@ -9921,6 +10357,7 @@ void cmdline(int argc, char **argv) { "Dump", no_argument, 0, 'D' }, { "debug", no_argument, 0, 'd' }, /* internal, not documented */ { "enable", required_argument, 0, 'e' }, + { "force", no_argument, 0, 'f' }, { "interval", required_argument, 0, 'i' }, { "IPC", no_argument, 0, 'I' }, { "num_iterations", required_argument, 0, 'n' }, @@ -9981,6 +10418,9 @@ void cmdline(int argc, char **argv) /* --enable specified counter */ bic_enabled = bic_enabled | bic_lookup(optarg, SHOW_LIST); break; + case 'f': + force_load++; + break; case 'd': debug++; ENABLE_BIC(BIC_DISABLED_BY_DEFAULT); diff --git a/tools/sched_ext/include/scx/common.bpf.h b/tools/sched_ext/include/scx/common.bpf.h index f3e15e9efa76..7849405614b1 100644 --- a/tools/sched_ext/include/scx/common.bpf.h +++ b/tools/sched_ext/include/scx/common.bpf.h @@ -270,8 +270,16 @@ void bpf_obj_drop_impl(void *kptr, void *meta) __ksym; #define bpf_obj_new(type) ((type *)bpf_obj_new_impl(bpf_core_type_id_local(type), NULL)) #define bpf_obj_drop(kptr) bpf_obj_drop_impl(kptr, NULL) -void bpf_list_push_front(struct bpf_list_head *head, struct bpf_list_node *node) __ksym; -void bpf_list_push_back(struct bpf_list_head *head, struct bpf_list_node *node) __ksym; +int bpf_list_push_front_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta, __u64 off) __ksym; +#define bpf_list_push_front(head, node) bpf_list_push_front_impl(head, node, NULL, 0) + +int bpf_list_push_back_impl(struct bpf_list_head *head, + struct bpf_list_node *node, + void *meta, __u64 off) __ksym; +#define bpf_list_push_back(head, node) bpf_list_push_back_impl(head, node, NULL, 0) + struct bpf_list_node *bpf_list_pop_front(struct bpf_list_head *head) __ksym; struct bpf_list_node *bpf_list_pop_back(struct bpf_list_head *head) __ksym; struct bpf_rb_node *bpf_rbtree_remove(struct bpf_rb_root *root, @@ -404,6 +412,17 @@ static __always_inline const struct cpumask *cast_mask(struct bpf_cpumask *mask) return (const struct cpumask *)mask; } +/* + * Return true if task @p cannot migrate to a different CPU, false + * otherwise. + */ +static inline bool is_migration_disabled(const struct task_struct *p) +{ + if (bpf_core_field_exists(p->migration_disabled)) + return p->migration_disabled; + return false; +} + /* rcu */ void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; @@ -421,7 +440,7 @@ void bpf_rcu_read_unlock(void) __ksym; */ static inline s64 time_delta(u64 after, u64 before) { - return (s64)(after - before) > 0 ? : 0; + return (s64)(after - before) > 0 ? (s64)(after - before) : 0; } /** diff --git a/tools/testing/cxl/test/mem.c b/tools/testing/cxl/test/mem.c index 347c1e7b37bd..8d731bd63988 100644 --- a/tools/testing/cxl/test/mem.c +++ b/tools/testing/cxl/test/mem.c @@ -401,6 +401,10 @@ struct cxl_test_gen_media gen_media = { .channel = 1, .rank = 30, }, + .component_id = { 0x3, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .cme_threshold_ev_flags = 3, + .cme_count = { 33, 0, 0 }, + .sub_type = 0x2, }, }; @@ -429,6 +433,11 @@ struct cxl_test_dram dram = { .bank_group = 5, .bank = 2, .column = {0xDE, 0xAD}, + .component_id = { 0x1, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .sub_channel = 8, + .cme_threshold_ev_flags = 2, + .cvme_count = { 14, 0, 0 }, + .sub_type = 0x5, }, }; @@ -456,7 +465,10 @@ struct cxl_test_mem_module mem_module = { .dirty_shutdown_cnt = { 0xde, 0xad, 0xbe, 0xef }, .cor_vol_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, .cor_per_err_cnt = { 0xde, 0xad, 0xbe, 0xef }, - } + }, + /* .validity_flags = <set below> */ + .component_id = { 0x2, 0x74, 0xc5, 0x8, 0x9a, 0x1a, 0xb, 0xfc, 0xd2, 0x7e, 0x2f, 0x31, 0x9b, 0x3c, 0x81, 0x4d }, + .event_sub_type = 0x3, }, }; @@ -478,13 +490,18 @@ static int mock_set_timestamp(struct cxl_dev_state *cxlds, static void cxl_mock_add_event_logs(struct mock_event_store *mes) { - put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK, + put_unaligned_le16(CXL_GMER_VALID_CHANNEL | CXL_GMER_VALID_RANK | + CXL_GMER_VALID_COMPONENT | CXL_GMER_VALID_COMPONENT_ID_FORMAT, &gen_media.rec.media_hdr.validity_flags); put_unaligned_le16(CXL_DER_VALID_CHANNEL | CXL_DER_VALID_BANK_GROUP | - CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN, + CXL_DER_VALID_BANK | CXL_DER_VALID_COLUMN | CXL_DER_VALID_SUB_CHANNEL | + CXL_DER_VALID_COMPONENT | CXL_DER_VALID_COMPONENT_ID_FORMAT, &dram.rec.media_hdr.validity_flags); + put_unaligned_le16(CXL_MMER_VALID_COMPONENT | CXL_MMER_VALID_COMPONENT_ID_FORMAT, + &mem_module.rec.validity_flags); + mes_add_event(mes, CXL_EVENT_TYPE_INFO, &maint_needed); mes_add_event(mes, CXL_EVENT_TYPE_INFO, (struct cxl_event_record_raw *)&gen_media); diff --git a/tools/testing/cxl/test/mock.c b/tools/testing/cxl/test/mock.c index 450c7566c33f..af2594e4f35d 100644 --- a/tools/testing/cxl/test/mock.c +++ b/tools/testing/cxl/test/mock.c @@ -228,16 +228,16 @@ int __wrap_cxl_hdm_decode_init(struct cxl_dev_state *cxlds, } EXPORT_SYMBOL_NS_GPL(__wrap_cxl_hdm_decode_init, "CXL"); -int __wrap_cxl_dvsec_rr_decode(struct device *dev, struct cxl_port *port, +int __wrap_cxl_dvsec_rr_decode(struct cxl_dev_state *cxlds, struct cxl_endpoint_dvsec_info *info) { int rc = 0, index; struct cxl_mock_ops *ops = get_cxl_mock_ops(&index); - if (ops && ops->is_mock_dev(dev)) + if (ops && ops->is_mock_dev(cxlds->dev)) rc = 0; else - rc = cxl_dvsec_rr_decode(dev, port, info); + rc = cxl_dvsec_rr_decode(cxlds, info); put_cxl_mock_ops(index); return rc; diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c index 3729fbfd3084..80b153d3ddec 100644 --- a/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c +++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector_classification.c @@ -542,8 +542,12 @@ static void detach_program(struct bpf_flow *skel, int prog_fd) static int set_port_drop(int pf, bool multi_port) { + char dst_port[16]; + + snprintf(dst_port, sizeof(dst_port), "%d", CFG_PORT_INNER); + SYS(fail, "tc qdisc add dev lo ingress"); - SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s", + SYS(fail_delete_qdisc, "tc filter add %s %s %s %s %s %s %s %s %s %s %s %s", "dev lo", "parent FFFF:", "protocol", pf == PF_INET6 ? "ipv6" : "ip", @@ -551,6 +555,7 @@ static int set_port_drop(int pf, bool multi_port) "flower", "ip_proto udp", "src_port", multi_port ? "8-10" : "9", + "dst_port", dst_port, "action drop"); return 0; diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c index f8953455db29..1e3e4392dcca 100644 --- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c +++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c @@ -111,31 +111,35 @@ out: static void test_sockmap_vsock_delete_on_close(void) { - int err, c, p, map; - const int zero = 0; - - err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); - if (!ASSERT_OK(err, "create_pair(AF_VSOCK)")) - return; + int map, c, p, err, zero = 0; map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), sizeof(int), 1, NULL); - if (!ASSERT_GE(map, 0, "bpf_map_create")) { - close(c); - goto out; - } + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; - err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); - close(c); - if (!ASSERT_OK(err, "bpf_map_update")) - goto out; + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; + + if (xbpf_map_update_elem(map, &zero, &c, BPF_NOEXIST)) + goto close_socks; + + xclose(c); + xclose(p); + + err = create_pair(AF_VSOCK, SOCK_STREAM, &c, &p); + if (!ASSERT_OK(err, "create_pair")) + goto close_map; - err = bpf_map_update_elem(map, &zero, &p, BPF_NOEXIST); + err = bpf_map_update_elem(map, &zero, &c, BPF_NOEXIST); ASSERT_OK(err, "after close(), bpf_map_update"); -out: - close(p); - close(map); +close_socks: + xclose(c); + xclose(p); +close_map: + xclose(map); } static void test_skmsg_helpers(enum bpf_map_type map_type) @@ -1010,6 +1014,34 @@ destroy: test_sockmap_pass_prog__destroy(skel); } +static void test_sockmap_vsock_unconnected(void) +{ + struct sockaddr_storage addr; + int map, s, zero = 0; + socklen_t alen; + + map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int), + sizeof(int), 1, NULL); + if (!ASSERT_OK_FD(map, "bpf_map_create")) + return; + + s = xsocket(AF_VSOCK, SOCK_STREAM, 0); + if (s < 0) + goto close_map; + + /* Fail connect(), but trigger transport assignment. */ + init_addr_loopback(AF_VSOCK, &addr, &alen); + if (!ASSERT_ERR(connect(s, sockaddr(&addr), alen), "connect")) + goto close_sock; + + ASSERT_ERR(bpf_map_update_elem(map, &zero, &s, BPF_ANY), "map_update"); + +close_sock: + xclose(s); +close_map: + xclose(map); +} + void test_sockmap_basic(void) { if (test__start_subtest("sockmap create_update_free")) @@ -1074,4 +1106,6 @@ void test_sockmap_basic(void) test_skmsg_helpers_with_link(BPF_MAP_TYPE_SOCKHASH); if (test__start_subtest("sockmap skb_verdict vsock poll")) test_sockmap_skb_verdict_vsock_poll(); + if (test__start_subtest("sockmap vsock unconnected")) + test_sockmap_vsock_unconnected(); } diff --git a/tools/testing/selftests/bpf/progs/find_vma.c b/tools/testing/selftests/bpf/progs/find_vma.c index 38034fb82530..02b82774469c 100644 --- a/tools/testing/selftests/bpf/progs/find_vma.c +++ b/tools/testing/selftests/bpf/progs/find_vma.c @@ -25,7 +25,7 @@ static long check_vma(struct task_struct *task, struct vm_area_struct *vma, { if (vma->vm_file) bpf_probe_read_kernel_str(d_iname, DNAME_INLINE_LEN - 1, - vma->vm_file->f_path.dentry->d_iname); + vma->vm_file->f_path.dentry->d_shortname.string); /* check for VM_EXEC */ if (vma->vm_flags & VM_EXEC) diff --git a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh index 3f45512fb512..7406c24be1ac 100755 --- a/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh +++ b/tools/testing/selftests/cgroup/test_cpuset_v1_hp.sh @@ -1,4 +1,4 @@ -#!/bin/sh +#!/bin/bash # SPDX-License-Identifier: GPL-2.0 # # Test the special cpuset v1 hotplug case where a cpuset become empty of diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index ca8a7edff3dd..319aaa004c40 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -252,6 +252,7 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True): try: # this targets queue 4, which doesn't exist ntuple2 = ethtool_create(cfg, "-N", flow) + defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}") except CmdExitFailure: pass else: @@ -259,7 +260,13 @@ def test_rss_queue_reconfigure(cfg, main_ctx=True): # change the table to target queues 0 and 2 ethtool(f"-X {cfg.ifname} {ctx_ref} weight 1 0 1 0") # ntuple rule therefore targets queues 1 and 3 - ntuple2 = ethtool_create(cfg, "-N", flow) + try: + ntuple2 = ethtool_create(cfg, "-N", flow) + except CmdExitFailure: + ksft_pr("Driver does not support rss + queue offset") + return + + defer(ethtool, f"-N {cfg.ifname} delete {ntuple2}") # should replace existing filter ksft_eq(ntuple, ntuple2) _send_traffic_check(cfg, port, ctx_ref, { 'target': (1, 3), diff --git a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh index 384cfa3d38a6..92c2f0376c08 100755 --- a/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh +++ b/tools/testing/selftests/drivers/net/netdevsim/udp_tunnel_nic.sh @@ -142,7 +142,7 @@ function pre_ethtool { } function check_table { - local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1 local -n expected=$2 local last=$3 @@ -212,7 +212,7 @@ function check_tables { } function print_table { - local path=$NSIM_DEV_DFS/ports/$port/udp_ports_table$1 + local path=$NSIM_DEV_DFS/ports/$port/udp_ports/table$1 read -a have < $path tree $NSIM_DEV_DFS/ @@ -641,7 +641,7 @@ for port in 0 1; do NSIM_NETDEV=`get_netdev_name old_netdevs` ip link set dev $NSIM_NETDEV up - echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + echo 110 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error msg="1 - create VxLANs v6" exp0=( 0 0 0 0 ) @@ -663,7 +663,7 @@ for port in 0 1; do new_geneve gnv0 20000 msg="2 - destroy GENEVE" - echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports_inject_error + echo 2 > $NSIM_DEV_DFS/ports/$port/udp_ports/inject_error exp1=( `mke 20000 2` 0 0 0 ) del_dev gnv0 @@ -764,7 +764,7 @@ for port in 0 1; do msg="create VxLANs v4" new_vxlan vxlan0 10000 $NSIM_NETDEV - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="NIC device goes down" @@ -775,7 +775,7 @@ for port in 0 1; do fi check_tables - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="NIC device goes up again" @@ -789,7 +789,7 @@ for port in 0 1; do del_dev vxlan0 check_tables - echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset + echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="destroy NIC" @@ -896,7 +896,7 @@ msg="vacate VxLAN in overflow table" exp0=( `mke 10000 1` `mke 10004 1` 0 `mke 10003 1` ) del_dev vxlan2 -echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports_reset +echo 1 > $NSIM_DEV_DFS/ports/$port/udp_ports/reset check_tables msg="tunnels destroyed 2" diff --git a/tools/testing/selftests/exec/check-exec.c b/tools/testing/selftests/exec/check-exec.c index 4d3f4525e1e1..55bce47e56b7 100644 --- a/tools/testing/selftests/exec/check-exec.c +++ b/tools/testing/selftests/exec/check-exec.c @@ -22,6 +22,7 @@ #include <sys/prctl.h> #include <sys/socket.h> #include <sys/stat.h> +#include <sys/syscall.h> #include <sys/sysmacros.h> #include <unistd.h> @@ -31,6 +32,12 @@ #include "../kselftest_harness.h" +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + static void drop_privileges(struct __test_metadata *const _metadata) { const unsigned int noroot = SECBIT_NOROOT | SECBIT_NOROOT_LOCKED; @@ -219,8 +226,8 @@ static void test_exec_fd(struct __test_metadata *_metadata, const int fd, * test framework as an error. With AT_EXECVE_CHECK, we only check a * potential successful execution. */ - access_ret = - execveat(fd, "", argv, NULL, AT_EMPTY_PATH | AT_EXECVE_CHECK); + access_ret = sys_execveat(fd, "", argv, NULL, + AT_EMPTY_PATH | AT_EXECVE_CHECK); access_errno = errno; if (err_code) { EXPECT_EQ(-1, access_ret); diff --git a/tools/testing/selftests/filesystems/statmount/statmount_test.c b/tools/testing/selftests/filesystems/statmount/statmount_test.c index 8eb6aa606a0d..46d289611ce8 100644 --- a/tools/testing/selftests/filesystems/statmount/statmount_test.c +++ b/tools/testing/selftests/filesystems/statmount/statmount_test.c @@ -383,6 +383,10 @@ static void test_statmount_mnt_point(void) return; } + if (!(sm->mask & STATMOUNT_MNT_POINT)) { + ksft_test_result_fail("missing STATMOUNT_MNT_POINT in mask\n"); + return; + } if (strcmp(sm->str + sm->mnt_point, "/") != 0) { ksft_test_result_fail("unexpected mount point: '%s' != '/'\n", sm->str + sm->mnt_point); @@ -408,6 +412,10 @@ static void test_statmount_mnt_root(void) strerror(errno)); return; } + if (!(sm->mask & STATMOUNT_MNT_ROOT)) { + ksft_test_result_fail("missing STATMOUNT_MNT_ROOT in mask\n"); + return; + } mnt_root = sm->str + sm->mnt_root; last_root = strrchr(mnt_root, '/'); if (last_root) @@ -437,6 +445,10 @@ static void test_statmount_fs_type(void) strerror(errno)); return; } + if (!(sm->mask & STATMOUNT_FS_TYPE)) { + ksft_test_result_fail("missing STATMOUNT_FS_TYPE in mask\n"); + return; + } fs_type = sm->str + sm->fs_type; for (s = known_fs; s != NULL; s++) { if (strcmp(fs_type, *s) == 0) @@ -464,6 +476,11 @@ static void test_statmount_mnt_opts(void) return; } + if (!(sm->mask & STATMOUNT_MNT_BASIC)) { + ksft_test_result_fail("missing STATMOUNT_MNT_BASIC in mask\n"); + return; + } + while (getline(&line, &len, f_mountinfo) != -1) { int i; char *p, *p2; @@ -514,7 +531,10 @@ static void test_statmount_mnt_opts(void) if (p2) *p2 = '\0'; - statmount_opts = sm->str + sm->mnt_opts; + if (sm->mask & STATMOUNT_MNT_OPTS) + statmount_opts = sm->str + sm->mnt_opts; + else + statmount_opts = ""; if (strcmp(statmount_opts, p) != 0) ksft_test_result_fail( "unexpected mount options: '%s' != '%s'\n", diff --git a/tools/testing/selftests/gpio/gpio-sim.sh b/tools/testing/selftests/gpio/gpio-sim.sh index 6fb66a687f17..bbc29ed9c60a 100755 --- a/tools/testing/selftests/gpio/gpio-sim.sh +++ b/tools/testing/selftests/gpio/gpio-sim.sh @@ -46,12 +46,6 @@ remove_chip() { rmdir $CONFIGFS_DIR/$CHIP || fail "Unable to remove the chip" } -configfs_cleanup() { - for CHIP in `ls $CONFIGFS_DIR/`; do - remove_chip $CHIP - done -} - create_chip() { local CHIP=$1 @@ -105,6 +99,13 @@ disable_chip() { echo 0 > $CONFIGFS_DIR/$CHIP/live || fail "Unable to disable the chip" } +configfs_cleanup() { + for CHIP in `ls $CONFIGFS_DIR/`; do + disable_chip $CHIP + remove_chip $CHIP + done +} + configfs_chip_name() { local CHIP=$1 local BANK=$2 @@ -181,6 +182,7 @@ create_chip chip create_bank chip bank enable_chip chip test -n `cat $CONFIGFS_DIR/chip/bank/chip_name` || fail "chip_name doesn't work" +disable_chip chip remove_chip chip echo "1.2. chip_name returns 'none' if the chip is still pending" @@ -195,6 +197,7 @@ create_chip chip create_bank chip bank enable_chip chip test -n `cat $CONFIGFS_DIR/chip/dev_name` || fail "dev_name doesn't work" +disable_chip chip remove_chip chip echo "2. Creating and configuring simulated chips" @@ -204,6 +207,7 @@ create_chip chip create_bank chip bank enable_chip chip test "`get_chip_num_lines chip bank`" = "1" || fail "default number of lines is not 1" +disable_chip chip remove_chip chip echo "2.2. Number of lines can be specified" @@ -212,6 +216,7 @@ create_bank chip bank set_num_lines chip bank 16 enable_chip chip test "`get_chip_num_lines chip bank`" = "16" || fail "number of lines is not 16" +disable_chip chip remove_chip chip echo "2.3. Label can be set" @@ -220,6 +225,7 @@ create_bank chip bank set_label chip bank foobar enable_chip chip test "`get_chip_label chip bank`" = "foobar" || fail "label is incorrect" +disable_chip chip remove_chip chip echo "2.4. Label can be left empty" @@ -227,6 +233,7 @@ create_chip chip create_bank chip bank enable_chip chip test -z "`cat $CONFIGFS_DIR/chip/bank/label`" || fail "label is not empty" +disable_chip chip remove_chip chip echo "2.5. Line names can be configured" @@ -238,6 +245,7 @@ set_line_name chip bank 2 bar enable_chip chip test "`get_line_name chip bank 0`" = "foo" || fail "line name is incorrect" test "`get_line_name chip bank 2`" = "bar" || fail "line name is incorrect" +disable_chip chip remove_chip chip echo "2.6. Line config can remain unused if offset is greater than number of lines" @@ -248,6 +256,7 @@ set_line_name chip bank 5 foobar enable_chip chip test "`get_line_name chip bank 0`" = "" || fail "line name is incorrect" test "`get_line_name chip bank 1`" = "" || fail "line name is incorrect" +disable_chip chip remove_chip chip echo "2.7. Line configfs directory names are sanitized" @@ -267,6 +276,7 @@ for CHIP in $CHIPS; do enable_chip $CHIP done for CHIP in $CHIPS; do + disable_chip $CHIP remove_chip $CHIP done @@ -278,6 +288,7 @@ echo foobar > $CONFIGFS_DIR/chip/bank/label 2> /dev/null && \ fail "Setting label of a live chip should fail" echo 8 > $CONFIGFS_DIR/chip/bank/num_lines 2> /dev/null && \ fail "Setting number of lines of a live chip should fail" +disable_chip chip remove_chip chip echo "2.10. Can't create line items when chip is live" @@ -285,6 +296,7 @@ create_chip chip create_bank chip bank enable_chip chip mkdir $CONFIGFS_DIR/chip/bank/line0 2> /dev/null && fail "Creating line item should fail" +disable_chip chip remove_chip chip echo "2.11. Probe errors are propagated to user-space" @@ -316,6 +328,7 @@ mkdir -p $CONFIGFS_DIR/chip/bank/line4/hog enable_chip chip $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 4 2> /dev/null && \ fail "Setting the value of a hogged line shouldn't succeed" +disable_chip chip remove_chip chip echo "3. Controlling simulated chips" @@ -331,6 +344,7 @@ test "$?" = "1" || fail "pull set incorrectly" sysfs_set_pull chip bank 0 pull-down $BASE_DIR/gpio-mockup-cdev /dev/`configfs_chip_name chip bank` 1 test "$?" = "0" || fail "pull set incorrectly" +disable_chip chip remove_chip chip echo "3.2. Pull can be read from sysfs" @@ -344,6 +358,7 @@ SYSFS_PATH=/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull test `cat $SYSFS_PATH` = "pull-down" || fail "reading the pull failed" sysfs_set_pull chip bank 0 pull-up test `cat $SYSFS_PATH` = "pull-up" || fail "reading the pull failed" +disable_chip chip remove_chip chip echo "3.3. Incorrect input in sysfs is rejected" @@ -355,6 +370,7 @@ DEVNAME=`configfs_dev_name chip` CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/pull" echo foobar > $SYSFS_PATH 2> /dev/null && fail "invalid input not detected" +disable_chip chip remove_chip chip echo "3.4. Can't write to value" @@ -365,6 +381,7 @@ DEVNAME=`configfs_dev_name chip` CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" echo 1 > $SYSFS_PATH 2> /dev/null && fail "writing to 'value' succeeded unexpectedly" +disable_chip chip remove_chip chip echo "4. Simulated GPIO chips are functional" @@ -382,6 +399,7 @@ $BASE_DIR/gpio-mockup-cdev -s 1 /dev/`configfs_chip_name chip bank` 0 & sleep 0.1 # FIXME Any better way? test `cat $SYSFS_PATH` = "1" || fail "incorrect value read from sysfs" kill $! +disable_chip chip remove_chip chip echo "4.2. Bias settings work correctly" @@ -394,6 +412,7 @@ CHIPNAME=`configfs_chip_name chip bank` SYSFS_PATH="/sys/devices/platform/$DEVNAME/$CHIPNAME/sim_gpio0/value" $BASE_DIR/gpio-mockup-cdev -b pull-up /dev/`configfs_chip_name chip bank` 0 test `cat $SYSFS_PATH` = "1" || fail "bias setting does not work" +disable_chip chip remove_chip chip echo "GPIO $MODULE test PASS" diff --git a/tools/testing/selftests/kvm/s390/cmma_test.c b/tools/testing/selftests/kvm/s390/cmma_test.c index e32dd59703a0..85cc8c18d6e7 100644 --- a/tools/testing/selftests/kvm/s390/cmma_test.c +++ b/tools/testing/selftests/kvm/s390/cmma_test.c @@ -444,7 +444,7 @@ static void assert_no_pages_cmma_dirty(struct kvm_vm *vm) ); } -static void test_get_inital_dirty(void) +static void test_get_initial_dirty(void) { struct kvm_vm *vm = create_vm_two_memslots(); struct kvm_vcpu *vcpu; @@ -651,7 +651,7 @@ struct testdef { } testlist[] = { { "migration mode and dirty tracking", test_migration_mode }, { "GET_CMMA_BITS: basic calls", test_get_cmma_basic }, - { "GET_CMMA_BITS: all pages are dirty initally", test_get_inital_dirty }, + { "GET_CMMA_BITS: all pages are dirty initially", test_get_initial_dirty }, { "GET_CMMA_BITS: holes are skipped", test_get_skip_holes }, }; diff --git a/tools/testing/selftests/kvm/s390/ucontrol_test.c b/tools/testing/selftests/kvm/s390/ucontrol_test.c index 135ee22856cf..d265b34c54be 100644 --- a/tools/testing/selftests/kvm/s390/ucontrol_test.c +++ b/tools/testing/selftests/kvm/s390/ucontrol_test.c @@ -88,10 +88,6 @@ asm("test_skey_asm:\n" " ahi %r0,1\n" " st %r1,0(%r5,%r6)\n" - " iske %r1,%r6\n" - " ahi %r0,1\n" - " diag 0,0,0x44\n" - " sske %r1,%r6\n" " xgr %r1,%r1\n" " iske %r1,%r6\n" @@ -459,10 +455,14 @@ TEST_F(uc_kvm, uc_no_user_region) }; ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION, ®ion)); - ASSERT_EQ(EINVAL, errno); + ASSERT_TRUE(errno == EEXIST || errno == EINVAL) + TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION", + strerror(errno), errno); ASSERT_EQ(-1, ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION2, ®ion2)); - ASSERT_EQ(EINVAL, errno); + ASSERT_TRUE(errno == EEXIST || errno == EINVAL) + TH_LOG("errno %s (%i) not expected for ioctl KVM_SET_USER_MEMORY_REGION2", + strerror(errno), errno); } TEST_F(uc_kvm, uc_map_unmap) @@ -596,7 +596,9 @@ TEST_F(uc_kvm, uc_skey) ASSERT_EQ(true, uc_handle_exit(self)); ASSERT_EQ(1, sync_regs->gprs[0]); - /* ISKE */ + /* SSKE + ISKE */ + sync_regs->gprs[1] = skeyvalue; + run->kvm_dirty_regs |= KVM_SYNC_GPRS; ASSERT_EQ(0, uc_run_once(self)); /* @@ -608,21 +610,11 @@ TEST_F(uc_kvm, uc_skey) TEST_ASSERT_EQ(0, sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)); TEST_ASSERT_EQ(KVM_EXIT_S390_SIEIC, self->run->exit_reason); TEST_ASSERT_EQ(ICPT_INST, sie_block->icptcode); - TEST_REQUIRE(sie_block->ipa != 0xb229); + TEST_REQUIRE(sie_block->ipa != 0xb22b); - /* ISKE contd. */ + /* SSKE + ISKE contd. */ ASSERT_EQ(false, uc_handle_exit(self)); ASSERT_EQ(2, sync_regs->gprs[0]); - /* assert initial skey (ACC = 0, R & C = 1) */ - ASSERT_EQ(0x06, sync_regs->gprs[1]); - uc_assert_diag44(self); - - /* SSKE + ISKE */ - sync_regs->gprs[1] = skeyvalue; - run->kvm_dirty_regs |= KVM_SYNC_GPRS; - ASSERT_EQ(0, uc_run_once(self)); - ASSERT_EQ(false, uc_handle_exit(self)); - ASSERT_EQ(3, sync_regs->gprs[0]); ASSERT_EQ(skeyvalue, sync_regs->gprs[1]); uc_assert_diag44(self); @@ -631,7 +623,7 @@ TEST_F(uc_kvm, uc_skey) run->kvm_dirty_regs |= KVM_SYNC_GPRS; ASSERT_EQ(0, uc_run_once(self)); ASSERT_EQ(false, uc_handle_exit(self)); - ASSERT_EQ(4, sync_regs->gprs[0]); + ASSERT_EQ(3, sync_regs->gprs[0]); /* assert R reset but rest of skey unchanged */ ASSERT_EQ(skeyvalue & 0xfa, sync_regs->gprs[1]); ASSERT_EQ(0, sync_regs->gprs[1] & 0x04); diff --git a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c index 4f5881d4ef66..4e920705681a 100644 --- a/tools/testing/selftests/kvm/x86/hyperv_cpuid.c +++ b/tools/testing/selftests/kvm/x86/hyperv_cpuid.c @@ -41,13 +41,19 @@ static bool smt_possible(void) return res; } -static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, - bool evmcs_expected) +static void test_hv_cpuid(struct kvm_vcpu *vcpu, bool evmcs_expected) { + const bool has_irqchip = !vcpu || vcpu->vm->has_irqchip; + const struct kvm_cpuid2 *hv_cpuid_entries; int i; int nent_expected = 10; u32 test_val; + if (vcpu) + hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); + else + hv_cpuid_entries = kvm_get_supported_hv_cpuid(); + TEST_ASSERT(hv_cpuid_entries->nent == nent_expected, "KVM_GET_SUPPORTED_HV_CPUID should return %d entries" " (returned %d)", @@ -80,12 +86,19 @@ static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, entry->eax, evmcs_expected ); break; + case 0x40000003: + TEST_ASSERT(has_irqchip || !(entry->edx & BIT(19)), + "\"Direct\" Synthetic Timers should require in-kernel APIC"); + break; case 0x40000004: test_val = entry->eax & (1UL << 18); TEST_ASSERT(!!test_val == !smt_possible(), "NoNonArchitecturalCoreSharing bit" " doesn't reflect SMT setting"); + + TEST_ASSERT(has_irqchip || !(entry->eax & BIT(10)), + "Cluster IPI (i.e. SEND_IPI) should require in-kernel APIC"); break; case 0x4000000A: TEST_ASSERT(entry->eax & (1UL << 19), @@ -109,9 +122,16 @@ static void test_hv_cpuid(const struct kvm_cpuid2 *hv_cpuid_entries, * entry->edx); */ } + + /* + * Note, the CPUID array returned by the system-scoped helper is a one- + * time allocation, i.e. must not be freed. + */ + if (vcpu) + free((void *)hv_cpuid_entries); } -void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) +static void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) { static struct kvm_cpuid2 cpuid = {.nent = 0}; int ret; @@ -129,19 +149,20 @@ void test_hv_cpuid_e2big(struct kvm_vm *vm, struct kvm_vcpu *vcpu) int main(int argc, char *argv[]) { struct kvm_vm *vm; - const struct kvm_cpuid2 *hv_cpuid_entries; struct kvm_vcpu *vcpu; TEST_REQUIRE(kvm_has_cap(KVM_CAP_HYPERV_CPUID)); - vm = vm_create_with_one_vcpu(&vcpu, guest_code); + /* Test the vCPU ioctl without an in-kernel local APIC. */ + vm = vm_create_barebones(); + vcpu = __vm_vcpu_add(vm, 0); + test_hv_cpuid(vcpu, false); + kvm_vm_free(vm); /* Test vCPU ioctl version */ + vm = vm_create_with_one_vcpu(&vcpu, guest_code); test_hv_cpuid_e2big(vm, vcpu); - - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); - test_hv_cpuid(hv_cpuid_entries, false); - free((void *)hv_cpuid_entries); + test_hv_cpuid(vcpu, false); if (!kvm_cpu_has(X86_FEATURE_VMX) || !kvm_has_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS)) { @@ -149,9 +170,7 @@ int main(int argc, char *argv[]) goto do_sys; } vcpu_enable_evmcs(vcpu); - hv_cpuid_entries = vcpu_get_supported_hv_cpuid(vcpu); - test_hv_cpuid(hv_cpuid_entries, true); - free((void *)hv_cpuid_entries); + test_hv_cpuid(vcpu, true); do_sys: /* Test system ioctl version */ @@ -161,9 +180,7 @@ do_sys: } test_hv_cpuid_e2big(vm, NULL); - - hv_cpuid_entries = kvm_get_supported_hv_cpuid(); - test_hv_cpuid(hv_cpuid_entries, kvm_cpu_has(X86_FEATURE_VMX)); + test_hv_cpuid(NULL, kvm_cpu_has(X86_FEATURE_VMX)); out: kvm_vm_free(vm); diff --git a/tools/testing/selftests/landlock/fs_test.c b/tools/testing/selftests/landlock/fs_test.c index 2af86bd796ba..aa6f2c1cbec7 100644 --- a/tools/testing/selftests/landlock/fs_test.c +++ b/tools/testing/selftests/landlock/fs_test.c @@ -59,6 +59,12 @@ int open_tree(int dfd, const char *filename, unsigned int flags) } #endif +static int sys_execveat(int dirfd, const char *pathname, char *const argv[], + char *const envp[], int flags) +{ + return syscall(__NR_execveat, dirfd, pathname, argv, envp, flags); +} + #ifndef RENAME_EXCHANGE #define RENAME_EXCHANGE (1 << 1) #endif @@ -2024,8 +2030,8 @@ static void test_check_exec(struct __test_metadata *const _metadata, int ret; char *const argv[] = { (char *)path, NULL }; - ret = execveat(AT_FDCWD, path, argv, NULL, - AT_EMPTY_PATH | AT_EXECVE_CHECK); + ret = sys_execveat(AT_FDCWD, path, argv, NULL, + AT_EMPTY_PATH | AT_EXECVE_CHECK); if (err) { EXPECT_EQ(-1, ret); EXPECT_EQ(errno, err); diff --git a/tools/testing/selftests/livepatch/functions.sh b/tools/testing/selftests/livepatch/functions.sh index e5d06fb40233..15601402dee6 100644 --- a/tools/testing/selftests/livepatch/functions.sh +++ b/tools/testing/selftests/livepatch/functions.sh @@ -306,7 +306,8 @@ function check_result { result=$(dmesg | awk -v last_dmesg="$LAST_DMESG" 'p; $0 == last_dmesg { p=1 }' | \ grep -e 'livepatch:' -e 'test_klp' | \ grep -v '\(tainting\|taints\) kernel' | \ - sed 's/^\[[ 0-9.]*\] //') + sed 's/^\[[ 0-9.]*\] //' | \ + sed 's/^\[[ ]*[CT][0-9]*\] //') if [[ "$expect" == "$result" ]] ; then echo "ok" diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 333c468c2699..da7e26668103 100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh @@ -220,7 +220,7 @@ run_test() { if test_selected ${CATEGORY}; then # On memory constrainted systems some tests can fail to allocate hugepages. # perform some cleanup before the test for a higher success rate. - if [ ${CATEGORY} == "thp" ] | [ ${CATEGORY} == "hugetlb" ]; then + if [ ${CATEGORY} == "thp" -o ${CATEGORY} == "hugetlb" ]; then echo 3 > /proc/sys/vm/drop_caches sleep 2 echo 1 > /proc/sys/vm/compact_memory diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py index d10f420e4ef6..fd0d959914e4 100755 --- a/tools/testing/selftests/net/bpf_offload.py +++ b/tools/testing/selftests/net/bpf_offload.py @@ -215,12 +215,14 @@ def bpftool_map_list_wait(expected=0, n_retry=20, ns=""): raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps)) def bpftool_prog_load(sample, file_name, maps=[], prog_type="xdp", dev=None, - fail=True, include_stderr=False): + fail=True, include_stderr=False, dev_bind=None): args = "prog load %s %s" % (os.path.join(bpf_test_dir, sample), file_name) if prog_type is not None: args += " type " + prog_type if dev is not None: args += " dev " + dev + elif dev_bind is not None: + args += " xdpmeta_dev " + dev_bind if len(maps): args += " map " + " map ".join(maps) @@ -980,6 +982,16 @@ try: rm("/sys/fs/bpf/offload") sim.wait_for_flush() + bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/devbound", + dev_bind=sim['ifname']) + devbound = bpf_pinned("/sys/fs/bpf/devbound") + start_test("Test dev-bound program in generic mode...") + ret, _, err = sim.set_xdp(devbound, "generic", fail=False, include_stderr=True) + fail(ret == 0, "devbound program in generic mode allowed") + check_extack(err, "Can't attach device-bound programs in generic mode.", args) + rm("/sys/fs/bpf/devbound") + sim.wait_for_flush() + start_test("Test XDP load failure...") sim.dfs["dev/bpf_bind_verifier_accept"] = 0 ret, _, err = bpftool_prog_load("sample_ret0.bpf.o", "/sys/fs/bpf/offload", diff --git a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh index 3885a2a91f7d..baed5e380dae 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower_port_range.sh @@ -20,6 +20,7 @@ ALL_TESTS=" test_port_range_ipv4_tcp test_port_range_ipv6_udp test_port_range_ipv6_tcp + test_port_range_ipv4_udp_drop " NUM_NETIFS=4 @@ -194,6 +195,51 @@ test_port_range_ipv6_tcp() __test_port_range $proto $ip_proto $sip $dip $mode "$name" } +test_port_range_ipv4_udp_drop() +{ + local proto=ipv4 + local ip_proto=udp + local sip=192.0.2.1 + local dip=192.0.2.2 + local mode="-4" + local name="IPv4 UDP Drop" + local dmac=$(mac_get $h2) + local smac=$(mac_get $h1) + local sport_min=2000 + local sport_max=3000 + local sport_mid=$((sport_min + (sport_max - sport_min) / 2)) + local dport=5000 + + RET=0 + + tc filter add dev $swp1 ingress protocol $proto handle 101 pref 1 \ + flower src_ip $sip dst_ip $dip ip_proto $ip_proto \ + src_port $sport_min-$sport_max \ + dst_port $dport \ + action drop + + # Test ports outside range - should pass + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_min - 1)),dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$((sport_max + 1)),dp=$dport" + + # Test ports inside range - should be dropped + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_min,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_mid,dp=$dport" + $MZ $mode $h1 -c 1 -q -p 100 -a $smac -b $dmac -A $sip -B $dip \ + -t $ip_proto "sp=$sport_max,dp=$dport" + + tc_check_packets "dev $swp1 ingress" 101 3 + check_err $? "Filter did not drop the expected number of packets" + + tc filter del dev $swp1 ingress protocol $proto pref 1 handle 101 flower + + log_test "Port range matching - $name" +} + setup_prepare() { h1=${NETIFS[p1]} diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile index 18b9443454a9..bc6b6762baf3 100644 --- a/tools/testing/selftests/net/lib/Makefile +++ b/tools/testing/selftests/net/lib/Makefile @@ -1,6 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../../usr/include/ $(KHDR_INCLUDES) # Additional include paths needed by kselftest.h CFLAGS += -I../../ diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile index 8e3fc05a5397..c76525fe2b84 100644 --- a/tools/testing/selftests/net/mptcp/Makefile +++ b/tools/testing/selftests/net/mptcp/Makefile @@ -2,7 +2,7 @@ top_srcdir = ../../../../.. -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \ simult_flows.sh mptcp_sockopt.sh userspace_pm.sh diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c index 414addef9a45..d240d02fa443 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_connect.c +++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c @@ -1302,7 +1302,7 @@ again: return ret; if (cfg_truncate > 0) { - xdisconnect(fd); + shutdown(fd, SHUT_WR); } else if (--cfg_repeat > 0) { xdisconnect(fd); diff --git a/tools/testing/selftests/net/openvswitch/Makefile b/tools/testing/selftests/net/openvswitch/Makefile index 2f1508abc826..3fd1da2ec07d 100644 --- a/tools/testing/selftests/net/openvswitch/Makefile +++ b/tools/testing/selftests/net/openvswitch/Makefile @@ -2,7 +2,7 @@ top_srcdir = ../../../../.. -CFLAGS = -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) +CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INCLUDES) TEST_PROGS := openvswitch.sh diff --git a/tools/testing/selftests/net/packetdrill/ksft_runner.sh b/tools/testing/selftests/net/packetdrill/ksft_runner.sh index e15c43b7359b..ef8b25a606d8 100755 --- a/tools/testing/selftests/net/packetdrill/ksft_runner.sh +++ b/tools/testing/selftests/net/packetdrill/ksft_runner.sh @@ -39,11 +39,13 @@ if [[ -n "${KSFT_MACHINE_SLOW}" ]]; then # xfail tests that are known flaky with dbg config, not fixable. # still run them for coverage (and expect 100% pass without dbg). declare -ar xfail_list=( + "tcp_eor_no-coalesce-retrans.pkt" "tcp_fast_recovery_prr-ss.*.pkt" + "tcp_slow_start_slow-start-after-win-update.pkt" "tcp_timestamping.*.pkt" "tcp_user_timeout_user-timeout-probe.pkt" "tcp_zerocopy_epoll_.*.pkt" - "tcp_tcp_info_tcp-info-*-limited.pkt" + "tcp_tcp_info_tcp-info-.*-limited.pkt" ) readonly xfail_regex="^($(printf '%s|' "${xfail_list[@]}"))$" [[ "$script" =~ ${xfail_regex} ]] && failfunc=ktap_test_xfail diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c index 3f2fca02fec5..36ff28af4b19 100644 --- a/tools/testing/selftests/net/udpgso.c +++ b/tools/testing/selftests/net/udpgso.c @@ -103,6 +103,19 @@ struct testcase testcases_v4[] = { .r_num_mss = 1, }, { + /* datalen <= MSS < gso_len: will fall back to no GSO */ + .tlen = CONST_MSS_V4, + .gso_len = CONST_MSS_V4 + 1, + .r_num_mss = 0, + .r_len_last = CONST_MSS_V4, + }, + { + /* MSS < datalen < gso_len: fail */ + .tlen = CONST_MSS_V4 + 1, + .gso_len = CONST_MSS_V4 + 2, + .tfail = true, + }, + { /* send a single MSS + 1B */ .tlen = CONST_MSS_V4 + 1, .gso_len = CONST_MSS_V4, @@ -206,6 +219,19 @@ struct testcase testcases_v6[] = { .r_num_mss = 1, }, { + /* datalen <= MSS < gso_len: will fall back to no GSO */ + .tlen = CONST_MSS_V6, + .gso_len = CONST_MSS_V6 + 1, + .r_num_mss = 0, + .r_len_last = CONST_MSS_V6, + }, + { + /* MSS < datalen < gso_len: fail */ + .tlen = CONST_MSS_V6 + 1, + .gso_len = CONST_MSS_V6 + 2, + .tfail = true + }, + { /* send a single MSS + 1B */ .tlen = CONST_MSS_V6 + 1, .gso_len = CONST_MSS_V6, diff --git a/tools/testing/selftests/riscv/vector/.gitignore b/tools/testing/selftests/riscv/vector/.gitignore index 9ae7964491d5..7d9c87cd0649 100644 --- a/tools/testing/selftests/riscv/vector/.gitignore +++ b/tools/testing/selftests/riscv/vector/.gitignore @@ -1,3 +1,4 @@ vstate_exec_nolibc vstate_prctl -v_initval_nolibc +v_initval +v_exec_initval_nolibc diff --git a/tools/testing/selftests/riscv/vector/Makefile b/tools/testing/selftests/riscv/vector/Makefile index bfff0ff4f3be..6f7497f4e7b3 100644 --- a/tools/testing/selftests/riscv/vector/Makefile +++ b/tools/testing/selftests/riscv/vector/Makefile @@ -2,18 +2,27 @@ # Copyright (C) 2021 ARM Limited # Originally tools/testing/arm64/abi/Makefile -TEST_GEN_PROGS := vstate_prctl v_initval_nolibc -TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc +TEST_GEN_PROGS := v_initval vstate_prctl +TEST_GEN_PROGS_EXTENDED := vstate_exec_nolibc v_exec_initval_nolibc include ../../lib.mk -$(OUTPUT)/vstate_prctl: vstate_prctl.c ../hwprobe/sys_hwprobe.S +$(OUTPUT)/sys_hwprobe.o: ../hwprobe/sys_hwprobe.S + $(CC) -static -c -o$@ $(CFLAGS) $^ + +$(OUTPUT)/v_helpers.o: v_helpers.c + $(CC) -static -c -o$@ $(CFLAGS) $^ + +$(OUTPUT)/vstate_prctl: vstate_prctl.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ $(OUTPUT)/vstate_exec_nolibc: vstate_exec_nolibc.c $(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \ -Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc -$(OUTPUT)/v_initval_nolibc: v_initval_nolibc.c +$(OUTPUT)/v_initval: v_initval.c $(OUTPUT)/sys_hwprobe.o $(OUTPUT)/v_helpers.o + $(CC) -static -o$@ $(CFLAGS) $(LDFLAGS) $^ + +$(OUTPUT)/v_exec_initval_nolibc: v_exec_initval_nolibc.c $(CC) -nostdlib -static -include ../../../../include/nolibc/nolibc.h \ -Wall $(CFLAGS) $(LDFLAGS) $^ -o $@ -lgcc diff --git a/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c new file mode 100644 index 000000000000..35c0812e32de --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_exec_initval_nolibc.c @@ -0,0 +1,94 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Get values of vector registers as soon as the program starts to test if + * is properly cleaning the values before starting a new program. Vector + * registers are caller saved, so no function calls may happen before reading + * the values. To further ensure consistency, this file is compiled without + * libc and without auto-vectorization. + * + * To be "clean" all values must be either all ones or all zeroes. + */ + +#define __stringify_1(x...) #x +#define __stringify(x...) __stringify_1(x) + +int main(int argc, char **argv) +{ + char prev_value = 0, value; + unsigned long vl; + int first = 1; + + if (argc > 2 && strcmp(argv[2], "x")) + asm volatile ( + // 0 | zimm[10:0] | rs1 | 1 1 1 | rd |1010111| vsetvli + // vsetvli t4, x0, e8, m1, d1 + ".4byte 0b00000000000000000111111011010111\n\t" + "mv %[vl], t4\n\t" + : [vl] "=r" (vl) : : "t4" + ); + else + asm volatile ( + ".option push\n\t" + ".option arch, +v\n\t" + "vsetvli %[vl], x0, e8, m1, ta, ma\n\t" + ".option pop\n\t" + : [vl] "=r" (vl) + ); + +#define CHECK_VECTOR_REGISTER(register) ({ \ + for (int i = 0; i < vl; i++) { \ + asm volatile ( \ + ".option push\n\t" \ + ".option arch, +v\n\t" \ + "vmv.x.s %0, " __stringify(register) "\n\t" \ + "vsrl.vi " __stringify(register) ", " __stringify(register) ", 8\n\t" \ + ".option pop\n\t" \ + : "=r" (value)); \ + if (first) { \ + first = 0; \ + } else if (value != prev_value || !(value == 0x00 || value == 0xff)) { \ + printf("Register " __stringify(register) \ + " values not clean! value: %u\n", value); \ + exit(-1); \ + } \ + prev_value = value; \ + } \ +}) + + CHECK_VECTOR_REGISTER(v0); + CHECK_VECTOR_REGISTER(v1); + CHECK_VECTOR_REGISTER(v2); + CHECK_VECTOR_REGISTER(v3); + CHECK_VECTOR_REGISTER(v4); + CHECK_VECTOR_REGISTER(v5); + CHECK_VECTOR_REGISTER(v6); + CHECK_VECTOR_REGISTER(v7); + CHECK_VECTOR_REGISTER(v8); + CHECK_VECTOR_REGISTER(v9); + CHECK_VECTOR_REGISTER(v10); + CHECK_VECTOR_REGISTER(v11); + CHECK_VECTOR_REGISTER(v12); + CHECK_VECTOR_REGISTER(v13); + CHECK_VECTOR_REGISTER(v14); + CHECK_VECTOR_REGISTER(v15); + CHECK_VECTOR_REGISTER(v16); + CHECK_VECTOR_REGISTER(v17); + CHECK_VECTOR_REGISTER(v18); + CHECK_VECTOR_REGISTER(v19); + CHECK_VECTOR_REGISTER(v20); + CHECK_VECTOR_REGISTER(v21); + CHECK_VECTOR_REGISTER(v22); + CHECK_VECTOR_REGISTER(v23); + CHECK_VECTOR_REGISTER(v24); + CHECK_VECTOR_REGISTER(v25); + CHECK_VECTOR_REGISTER(v26); + CHECK_VECTOR_REGISTER(v27); + CHECK_VECTOR_REGISTER(v28); + CHECK_VECTOR_REGISTER(v29); + CHECK_VECTOR_REGISTER(v30); + CHECK_VECTOR_REGISTER(v31); + +#undef CHECK_VECTOR_REGISTER + + return 0; +} diff --git a/tools/testing/selftests/riscv/vector/v_helpers.c b/tools/testing/selftests/riscv/vector/v_helpers.c new file mode 100644 index 000000000000..01a8799dcb78 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_helpers.c @@ -0,0 +1,68 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../hwprobe/hwprobe.h" +#include <asm/vendor/thead.h> +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <unistd.h> +#include <sys/wait.h> + +bool is_xtheadvector_supported(void) +{ + struct riscv_hwprobe pair; + + pair.key = RISCV_HWPROBE_KEY_VENDOR_EXT_THEAD_0; + riscv_hwprobe(&pair, 1, 0, NULL, 0); + return pair.value & RISCV_HWPROBE_VENDOR_EXT_XTHEADVECTOR; +} + +bool is_vector_supported(void) +{ + struct riscv_hwprobe pair; + + pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; + riscv_hwprobe(&pair, 1, 0, NULL, 0); + return pair.value & RISCV_HWPROBE_EXT_ZVE32X; +} + +int launch_test(char *next_program, int test_inherit, int xtheadvector) +{ + char *exec_argv[4], *exec_envp[1]; + int rc, pid, status; + + pid = fork(); + if (pid < 0) { + printf("fork failed %d", pid); + return -1; + } + + if (!pid) { + exec_argv[0] = next_program; + exec_argv[1] = test_inherit != 0 ? "x" : NULL; + exec_argv[2] = xtheadvector != 0 ? "x" : NULL; + exec_argv[3] = NULL; + exec_envp[0] = NULL; + /* launch the program again to check inherit */ + rc = execve(next_program, exec_argv, exec_envp); + if (rc) { + perror("execve"); + printf("child execve failed %d\n", rc); + exit(-1); + } + } + + rc = waitpid(-1, &status, 0); + if (rc < 0) { + printf("waitpid failed\n"); + return -3; + } + + if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) || + WIFSIGNALED(status)) { + printf("child exited abnormally\n"); + return -4; + } + + return WEXITSTATUS(status); +} diff --git a/tools/testing/selftests/riscv/vector/v_helpers.h b/tools/testing/selftests/riscv/vector/v_helpers.h new file mode 100644 index 000000000000..763cddfe26da --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_helpers.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +#include <stdbool.h> + +bool is_xtheadvector_supported(void); + +bool is_vector_supported(void); + +int launch_test(char *next_program, int test_inherit, int xtheadvector); diff --git a/tools/testing/selftests/riscv/vector/v_initval.c b/tools/testing/selftests/riscv/vector/v_initval.c new file mode 100644 index 000000000000..be9e1d18ad29 --- /dev/null +++ b/tools/testing/selftests/riscv/vector/v_initval.c @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include "../../kselftest_harness.h" +#include "v_helpers.h" + +#define NEXT_PROGRAM "./v_exec_initval_nolibc" + +TEST(v_initval) +{ + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + + ASSERT_EQ(0, launch_test(NEXT_PROGRAM, 0, xtheadvector)); +} + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c b/tools/testing/selftests/riscv/vector/v_initval_nolibc.c deleted file mode 100644 index 6174ffe016dc..000000000000 --- a/tools/testing/selftests/riscv/vector/v_initval_nolibc.c +++ /dev/null @@ -1,72 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only - -#include "../../kselftest.h" -#define MAX_VSIZE (8192 * 32) - -void dump(char *ptr, int size) -{ - int i = 0; - - for (i = 0; i < size; i++) { - if (i != 0) { - if (i % 16 == 0) - printf("\n"); - else if (i % 8 == 0) - printf(" "); - } - printf("%02x ", ptr[i]); - } - printf("\n"); -} - -int main(void) -{ - int i; - unsigned long vl; - char *datap, *tmp; - - ksft_set_plan(1); - - datap = malloc(MAX_VSIZE); - if (!datap) { - ksft_test_result_fail("fail to allocate memory for size = %d\n", MAX_VSIZE); - exit(-1); - } - - tmp = datap; - asm volatile ( - ".option push\n\t" - ".option arch, +v\n\t" - "vsetvli %0, x0, e8, m8, ta, ma\n\t" - "vse8.v v0, (%2)\n\t" - "add %1, %2, %0\n\t" - "vse8.v v8, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v16, (%1)\n\t" - "add %1, %1, %0\n\t" - "vse8.v v24, (%1)\n\t" - ".option pop\n\t" - : "=&r" (vl), "=r" (tmp) : "r" (datap) : "memory"); - - ksft_print_msg("vl = %lu\n", vl); - - if (datap[0] != 0x00 && datap[0] != 0xff) { - ksft_test_result_fail("v-regesters are not properly initialized\n"); - dump(datap, vl * 4); - exit(-1); - } - - for (i = 1; i < vl * 4; i++) { - if (datap[i] != datap[0]) { - ksft_test_result_fail("detect stale values on v-regesters\n"); - dump(datap, vl * 4); - exit(-2); - } - } - - free(datap); - - ksft_test_result_pass("tests for v_initval_nolibc pass\n"); - ksft_exit_pass(); - return 0; -} diff --git a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c index 1f9969bed235..7b7d6f21acb4 100644 --- a/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c +++ b/tools/testing/selftests/riscv/vector/vstate_exec_nolibc.c @@ -6,13 +6,16 @@ int main(int argc, char **argv) { - int rc, pid, status, test_inherit = 0; + int rc, pid, status, test_inherit = 0, xtheadvector = 0; long ctrl, ctrl_c; char *exec_argv[2], *exec_envp[2]; - if (argc > 1) + if (argc > 1 && strcmp(argv[1], "x")) test_inherit = 1; + if (argc > 2 && strcmp(argv[2], "x")) + xtheadvector = 1; + ctrl = my_syscall1(__NR_prctl, PR_RISCV_V_GET_CONTROL); if (ctrl < 0) { puts("PR_RISCV_V_GET_CONTROL is not supported\n"); @@ -53,11 +56,14 @@ int main(int argc, char **argv) puts("child's vstate_ctrl not equal to parent's\n"); exit(-1); } - asm volatile (".option push\n\t" - ".option arch, +v\n\t" - "vsetvli x0, x0, e32, m8, ta, ma\n\t" - ".option pop\n\t" - ); + if (xtheadvector) + asm volatile (".4byte 0x00007ed7"); + else + asm volatile (".option push\n\t" + ".option arch, +v\n\t" + "vsetvli x0, x0, e32, m8, ta, ma\n\t" + ".option pop\n\t" + ); exit(ctrl); } } diff --git a/tools/testing/selftests/riscv/vector/vstate_prctl.c b/tools/testing/selftests/riscv/vector/vstate_prctl.c index 40b3bffcbb40..62fbb17a0556 100644 --- a/tools/testing/selftests/riscv/vector/vstate_prctl.c +++ b/tools/testing/selftests/riscv/vector/vstate_prctl.c @@ -3,181 +3,244 @@ #include <unistd.h> #include <errno.h> #include <sys/wait.h> +#include <sys/types.h> +#include <stdlib.h> -#include "../hwprobe/hwprobe.h" -#include "../../kselftest.h" +#include "../../kselftest_harness.h" +#include "v_helpers.h" #define NEXT_PROGRAM "./vstate_exec_nolibc" -static int launch_test(int test_inherit) -{ - char *exec_argv[3], *exec_envp[1]; - int rc, pid, status; - - pid = fork(); - if (pid < 0) { - ksft_test_result_fail("fork failed %d", pid); - return -1; - } - if (!pid) { - exec_argv[0] = NEXT_PROGRAM; - exec_argv[1] = test_inherit != 0 ? "x" : NULL; - exec_argv[2] = NULL; - exec_envp[0] = NULL; - /* launch the program again to check inherit */ - rc = execve(NEXT_PROGRAM, exec_argv, exec_envp); - if (rc) { - perror("execve"); - ksft_test_result_fail("child execve failed %d\n", rc); - exit(-1); - } - } - - rc = waitpid(-1, &status, 0); - if (rc < 0) { - ksft_test_result_fail("waitpid failed\n"); - return -3; - } - - if ((WIFEXITED(status) && WEXITSTATUS(status) == -1) || - WIFSIGNALED(status)) { - ksft_test_result_fail("child exited abnormally\n"); - return -4; - } - - return WEXITSTATUS(status); -} - -int test_and_compare_child(long provided, long expected, int inherit) +int test_and_compare_child(long provided, long expected, int inherit, int xtheadvector) { int rc; rc = prctl(PR_RISCV_V_SET_CONTROL, provided); if (rc != 0) { - ksft_test_result_fail("prctl with provided arg %lx failed with code %d\n", - provided, rc); + printf("prctl with provided arg %lx failed with code %d\n", + provided, rc); return -1; } - rc = launch_test(inherit); + rc = launch_test(NEXT_PROGRAM, inherit, xtheadvector); if (rc != expected) { - ksft_test_result_fail("Test failed, check %d != %ld\n", rc, - expected); + printf("Test failed, check %d != %ld\n", rc, expected); return -2; } return 0; } -#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0 -#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2 +#define PR_RISCV_V_VSTATE_CTRL_CUR_SHIFT 0 +#define PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT 2 -int main(void) +TEST(get_control_no_v) { - struct riscv_hwprobe pair; - long flag, expected; long rc; - ksft_set_plan(1); + if (is_vector_supported() || is_xtheadvector_supported()) + SKIP(return, "Test expects vector to be not supported"); - pair.key = RISCV_HWPROBE_KEY_IMA_EXT_0; - rc = riscv_hwprobe(&pair, 1, 0, NULL, 0); - if (rc < 0) { - ksft_test_result_fail("hwprobe() failed with %ld\n", rc); - return -1; - } + rc = prctl(PR_RISCV_V_GET_CONTROL); + EXPECT_EQ(-1, rc) + TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X"); + EXPECT_EQ(EINVAL, errno) + TH_LOG("GET_CONTROL should fail on kernel/hw without ZVE32X"); +} - if (pair.key != RISCV_HWPROBE_KEY_IMA_EXT_0) { - ksft_test_result_fail("hwprobe cannot probe RISCV_HWPROBE_KEY_IMA_EXT_0\n"); - return -2; - } +TEST(set_control_no_v) +{ + long rc; - if (!(pair.value & RISCV_HWPROBE_EXT_ZVE32X)) { - rc = prctl(PR_RISCV_V_GET_CONTROL); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("GET_CONTROL should fail on kernel/hw without ZVE32X\n"); - return -3; - } - - rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("SET_CONTROL should fail on kernel/hw without ZVE32X\n"); - return -4; - } - - ksft_test_result_skip("Vector not supported\n"); - return 0; - } + if (is_vector_supported() || is_xtheadvector_supported()) + SKIP(return, "Test expects vector to be not supported"); + + rc = prctl(PR_RISCV_V_SET_CONTROL, PR_RISCV_V_VSTATE_CTRL_ON); + EXPECT_EQ(-1, rc) + TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X"); + EXPECT_EQ(EINVAL, errno) + TH_LOG("SET_CONTROL should fail on kernel/hw without ZVE32X"); +} + +TEST(vstate_on_current) +{ + long flag; + long rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); flag = PR_RISCV_V_VSTATE_CTRL_ON; rc = prctl(PR_RISCV_V_SET_CONTROL, flag); - if (rc != 0) { - ksft_test_result_fail("Enabling V for current should always success\n"); - return -5; - } + EXPECT_EQ(0, rc) TH_LOG("Enabling V for current should always succeed"); +} + +TEST(vstate_off_eperm) +{ + long flag; + long rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); flag = PR_RISCV_V_VSTATE_CTRL_OFF; rc = prctl(PR_RISCV_V_SET_CONTROL, flag); - if (rc != -1 || errno != EPERM) { - ksft_test_result_fail("Disabling current's V alive must fail with EPERM(%d)\n", - errno); - return -5; + EXPECT_EQ(EPERM, errno) + TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno); + EXPECT_EQ(-1, rc) + TH_LOG("Disabling V in current thread with V enabled must fail with EPERM(%d)", errno); +} + +TEST(vstate_on_no_nesting) +{ + long flag; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); } /* Turn on next's vector explicitly and test */ flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; - if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0)) - return -6; + + EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_ON, 0, xtheadvector)); +} + +TEST(vstate_off_nesting) +{ + long flag; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn off next's vector explicitly and test */ flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; - if (test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 0)) - return -7; + + EXPECT_EQ(0, test_and_compare_child(flag, PR_RISCV_V_VSTATE_CTRL_OFF, 1, xtheadvector)); +} + +TEST(vstate_on_inherit_no_nesting) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + + /* Turn on next's vector explicitly and test no inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_ON; + + EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector)); +} + +TEST(vstate_on_inherit) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn on next's vector explicitly and test inherit */ flag = PR_RISCV_V_VSTATE_CTRL_ON << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; expected = flag | PR_RISCV_V_VSTATE_CTRL_ON; - if (test_and_compare_child(flag, expected, 0)) - return -8; - if (test_and_compare_child(flag, expected, 1)) - return -9; + EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector)); +} + +TEST(vstate_off_inherit_no_nesting) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } + /* Turn off next's vector explicitly and test no inherit */ + flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; + flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; + expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF; + + EXPECT_EQ(0, test_and_compare_child(flag, expected, 0, xtheadvector)); +} + +TEST(vstate_off_inherit) +{ + long flag, expected; + int xtheadvector = 0; + + if (!is_vector_supported()) { + if (is_xtheadvector_supported()) + xtheadvector = 1; + else + SKIP(return, "Vector not supported"); + } /* Turn off next's vector explicitly and test inherit */ flag = PR_RISCV_V_VSTATE_CTRL_OFF << PR_RISCV_V_VSTATE_CTRL_NEXT_SHIFT; flag |= PR_RISCV_V_VSTATE_CTRL_INHERIT; expected = flag | PR_RISCV_V_VSTATE_CTRL_OFF; - if (test_and_compare_child(flag, expected, 0)) - return -10; - if (test_and_compare_child(flag, expected, 1)) - return -11; + EXPECT_EQ(0, test_and_compare_child(flag, expected, 1, xtheadvector)); +} + +/* arguments should fail with EINVAL */ +TEST(inval_set_control_1) +{ + int rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); - /* arguments should fail with EINVAL */ rc = prctl(PR_RISCV_V_SET_CONTROL, 0xff0); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} + +/* arguments should fail with EINVAL */ +TEST(inval_set_control_2) +{ + int rc; + + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); rc = prctl(PR_RISCV_V_SET_CONTROL, 0x3); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); +} - rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } +/* arguments should fail with EINVAL */ +TEST(inval_set_control_3) +{ + int rc; - rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); - if (rc != -1 || errno != EINVAL) { - ksft_test_result_fail("Undefined control argument should return EINVAL\n"); - return -12; - } + if (!is_vector_supported() && !is_xtheadvector_supported()) + SKIP(return, "Vector not supported"); - ksft_test_result_pass("tests for riscv_v_vstate_ctrl pass\n"); - ksft_exit_pass(); - return 0; + rc = prctl(PR_RISCV_V_SET_CONTROL, 0xc); + EXPECT_EQ(-1, rc); + EXPECT_EQ(EINVAL, errno); } + +TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/sched_ext/create_dsq.c b/tools/testing/selftests/sched_ext/create_dsq.c index fa946d9146d4..d67431f57ac6 100644 --- a/tools/testing/selftests/sched_ext/create_dsq.c +++ b/tools/testing/selftests/sched_ext/create_dsq.c @@ -14,11 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct create_dsq *skel; - skel = create_dsq__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = create_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(create_dsq__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c index e65d22f23f3b..b6d13496b24e 100644 --- a/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c +++ b/tools/testing/selftests/sched_ext/ddsp_bogus_dsq_fail.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct ddsp_bogus_dsq_fail *skel; - skel = ddsp_bogus_dsq_fail__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = ddsp_bogus_dsq_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_bogus_dsq_fail__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c index abafee587cd6..af9ce4ee8baa 100644 --- a/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c +++ b/tools/testing/selftests/sched_ext/ddsp_vtimelocal_fail.c @@ -14,8 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct ddsp_vtimelocal_fail *skel; - skel = ddsp_vtimelocal_fail__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = ddsp_vtimelocal_fail__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(ddsp_vtimelocal_fail__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c index fbda6bf54671..c02b2aa6fc64 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.bpf.c @@ -43,7 +43,7 @@ void BPF_STRUCT_OPS(dsp_local_on_dispatch, s32 cpu, struct task_struct *prev) if (!p) return; - if (p->nr_cpus_allowed == nr_cpus) + if (p->nr_cpus_allowed == nr_cpus && !is_migration_disabled(p)) target = bpf_get_prandom_u32() % nr_cpus; else target = scx_bpf_task_cpu(p); diff --git a/tools/testing/selftests/sched_ext/dsp_local_on.c b/tools/testing/selftests/sched_ext/dsp_local_on.c index 0ff27e57fe43..e1f2ce4abfe6 100644 --- a/tools/testing/selftests/sched_ext/dsp_local_on.c +++ b/tools/testing/selftests/sched_ext/dsp_local_on.c @@ -15,6 +15,7 @@ static enum scx_test_status setup(void **ctx) skel = dsp_local_on__open(); SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); skel->rodata->nr_cpus = libbpf_num_possible_cpus(); SCX_FAIL_IF(dsp_local_on__load(skel), "Failed to load skel"); diff --git a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c index 73e679953e27..d3387ae03679 100644 --- a/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c +++ b/tools/testing/selftests/sched_ext/enq_last_no_enq_fails.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct enq_last_no_enq_fails *skel; - skel = enq_last_no_enq_fails__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = enq_last_no_enq_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_last_no_enq_fails__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c index dd1350e5f002..a80e3a3b3698 100644 --- a/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c +++ b/tools/testing/selftests/sched_ext/enq_select_cpu_fails.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct enq_select_cpu_fails *skel; - skel = enq_select_cpu_fails__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = enq_select_cpu_fails__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(enq_select_cpu_fails__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/exit.c b/tools/testing/selftests/sched_ext/exit.c index 31bcd06e21cd..9451782689de 100644 --- a/tools/testing/selftests/sched_ext/exit.c +++ b/tools/testing/selftests/sched_ext/exit.c @@ -23,6 +23,7 @@ static enum scx_test_status run(void *ctx) char buf[16]; skel = exit__open(); + SCX_ENUM_INIT(skel); skel->rodata->exit_point = tc; exit__load(skel); link = bpf_map__attach_struct_ops(skel->maps.exit_ops); diff --git a/tools/testing/selftests/sched_ext/hotplug.c b/tools/testing/selftests/sched_ext/hotplug.c index 87bf220b1bce..1c9ceb661c43 100644 --- a/tools/testing/selftests/sched_ext/hotplug.c +++ b/tools/testing/selftests/sched_ext/hotplug.c @@ -49,8 +49,10 @@ static enum scx_test_status test_hotplug(bool onlining, bool cbs_defined) SCX_ASSERT(is_cpu_online()); - skel = hotplug__open_and_load(); - SCX_ASSERT(skel); + skel = hotplug__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(hotplug__load(skel), "Failed to load skel"); /* Testing the offline -> online path, so go offline before starting */ if (onlining) diff --git a/tools/testing/selftests/sched_ext/init_enable_count.c b/tools/testing/selftests/sched_ext/init_enable_count.c index 97d45f1e5597..eddf9e0e26e7 100644 --- a/tools/testing/selftests/sched_ext/init_enable_count.c +++ b/tools/testing/selftests/sched_ext/init_enable_count.c @@ -15,22 +15,6 @@ #define SCHED_EXT 7 -static struct init_enable_count * -open_load_prog(bool global) -{ - struct init_enable_count *skel; - - skel = init_enable_count__open(); - SCX_BUG_ON(!skel, "Failed to open skel"); - - if (!global) - skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL; - - SCX_BUG_ON(init_enable_count__load(skel), "Failed to load skel"); - - return skel; -} - static enum scx_test_status run_test(bool global) { struct init_enable_count *skel; @@ -40,7 +24,14 @@ static enum scx_test_status run_test(bool global) struct sched_param param = {}; pid_t pids[num_pre_forks]; - skel = open_load_prog(global); + skel = init_enable_count__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + + if (!global) + skel->struct_ops.init_enable_count_ops->flags |= SCX_OPS_SWITCH_PARTIAL; + + SCX_FAIL_IF(init_enable_count__load(skel), "Failed to load skel"); /* * Fork a bunch of children before we attach the scheduler so that we @@ -159,7 +150,7 @@ static enum scx_test_status run(void *ctx) struct scx_test init_enable_count = { .name = "init_enable_count", - .description = "Verify we do the correct amount of counting of init, " + .description = "Verify we correctly count the occurrences of init, " "enable, etc callbacks.", .run = run, }; diff --git a/tools/testing/selftests/sched_ext/maximal.c b/tools/testing/selftests/sched_ext/maximal.c index f38fc973c380..c6be50a9941d 100644 --- a/tools/testing/selftests/sched_ext/maximal.c +++ b/tools/testing/selftests/sched_ext/maximal.c @@ -14,8 +14,11 @@ static enum scx_test_status setup(void **ctx) { struct maximal *skel; - skel = maximal__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/maybe_null.c b/tools/testing/selftests/sched_ext/maybe_null.c index 31cfafb0cf65..aacf0c58ca4f 100644 --- a/tools/testing/selftests/sched_ext/maybe_null.c +++ b/tools/testing/selftests/sched_ext/maybe_null.c @@ -43,7 +43,7 @@ static enum scx_test_status run(void *ctx) struct scx_test maybe_null = { .name = "maybe_null", - .description = "Verify if PTR_MAYBE_NULL work for .dispatch", + .description = "Verify if PTR_MAYBE_NULL works for .dispatch", .run = run, }; REGISTER_SCX_TEST(&maybe_null) diff --git a/tools/testing/selftests/sched_ext/minimal.c b/tools/testing/selftests/sched_ext/minimal.c index 6c5db8ebbf8a..89f7261757ff 100644 --- a/tools/testing/selftests/sched_ext/minimal.c +++ b/tools/testing/selftests/sched_ext/minimal.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct minimal *skel; - skel = minimal__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = minimal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(minimal__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/prog_run.c b/tools/testing/selftests/sched_ext/prog_run.c index 3cd57ef8daaa..05974820ca69 100644 --- a/tools/testing/selftests/sched_ext/prog_run.c +++ b/tools/testing/selftests/sched_ext/prog_run.c @@ -15,11 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct prog_run *skel; - skel = prog_run__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = prog_run__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(prog_run__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/reload_loop.c b/tools/testing/selftests/sched_ext/reload_loop.c index 5cfba2d6e056..308211d80436 100644 --- a/tools/testing/selftests/sched_ext/reload_loop.c +++ b/tools/testing/selftests/sched_ext/reload_loop.c @@ -18,11 +18,10 @@ bool force_exit = false; static enum scx_test_status setup(void **ctx) { - skel = maximal__open_and_load(); - if (!skel) { - SCX_ERR("Failed to open and load skel"); - return SCX_TEST_FAIL; - } + skel = maximal__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(maximal__load(skel), "Failed to load skel"); return SCX_TEST_PASS; } diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl.c b/tools/testing/selftests/sched_ext/select_cpu_dfl.c index a53a40c2d2f0..5b6e045e1109 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dfl *skel; - skel = select_cpu_dfl__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dfl__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c index 1d85bf4bf3a3..9b5d232efb7f 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dfl_nodispatch.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dfl_nodispatch *skel; - skel = select_cpu_dfl_nodispatch__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dfl_nodispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dfl_nodispatch__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c index 0309ca8785b3..80283dbc41b7 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch.c @@ -17,8 +17,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch *skel; - skel = select_cpu_dispatch__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c index 47eb6ed7627d..5e72ebbc90a5 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_bad_dsq.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch_bad_dsq *skel; - skel = select_cpu_dispatch_bad_dsq__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch_bad_dsq__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_bad_dsq__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c index 48ff028a3c46..aa85949478bc 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c +++ b/tools/testing/selftests/sched_ext/select_cpu_dispatch_dbl_dsp.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_dispatch_dbl_dsp *skel; - skel = select_cpu_dispatch_dbl_dsp__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_dispatch_dbl_dsp__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_dispatch_dbl_dsp__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/sched_ext/select_cpu_vtime.c b/tools/testing/selftests/sched_ext/select_cpu_vtime.c index b4629c2364f5..1e9b5c9bfff1 100644 --- a/tools/testing/selftests/sched_ext/select_cpu_vtime.c +++ b/tools/testing/selftests/sched_ext/select_cpu_vtime.c @@ -15,8 +15,11 @@ static enum scx_test_status setup(void **ctx) { struct select_cpu_vtime *skel; - skel = select_cpu_vtime__open_and_load(); - SCX_FAIL_IF(!skel, "Failed to open and load skel"); + skel = select_cpu_vtime__open(); + SCX_FAIL_IF(!skel, "Failed to open"); + SCX_ENUM_INIT(skel); + SCX_FAIL_IF(select_cpu_vtime__load(skel), "Failed to load skel"); + *ctx = skel; return SCX_TEST_PASS; diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c index 8c3a73461475..14ba51b52095 100644 --- a/tools/testing/selftests/seccomp/seccomp_bpf.c +++ b/tools/testing/selftests/seccomp/seccomp_bpf.c @@ -47,6 +47,7 @@ #include <linux/kcmp.h> #include <sys/resource.h> #include <sys/capability.h> +#include <linux/perf_event.h> #include <unistd.h> #include <sys/syscall.h> @@ -68,6 +69,10 @@ # define PR_SET_PTRACER 0x59616d61 #endif +#ifndef noinline +#define noinline __attribute__((noinline)) +#endif + #ifndef PR_SET_NO_NEW_PRIVS #define PR_SET_NO_NEW_PRIVS 38 #define PR_GET_NO_NEW_PRIVS 39 @@ -4888,6 +4893,200 @@ TEST(tsync_vs_dead_thread_leader) EXPECT_EQ(0, status); } +noinline int probed(void) +{ + return 1; +} + +static int parse_uint_from_file(const char *file, const char *fmt) +{ + int err = -1, ret; + FILE *f; + + f = fopen(file, "re"); + if (f) { + err = fscanf(f, fmt, &ret); + fclose(f); + } + return err == 1 ? ret : err; +} + +static int determine_uprobe_perf_type(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/type"; + + return parse_uint_from_file(file, "%d\n"); +} + +static int determine_uprobe_retprobe_bit(void) +{ + const char *file = "/sys/bus/event_source/devices/uprobe/format/retprobe"; + + return parse_uint_from_file(file, "config:%d\n"); +} + +static ssize_t get_uprobe_offset(const void *addr) +{ + size_t start, base, end; + bool found = false; + char buf[256]; + FILE *f; + + f = fopen("/proc/self/maps", "r"); + if (!f) + return -1; + + while (fscanf(f, "%zx-%zx %s %zx %*[^\n]\n", &start, &end, buf, &base) == 4) { + if (buf[2] == 'x' && (uintptr_t)addr >= start && (uintptr_t)addr < end) { + found = true; + break; + } + } + fclose(f); + return found ? (uintptr_t)addr - start + base : -1; +} + +FIXTURE(URETPROBE) { + int fd; +}; + +FIXTURE_VARIANT(URETPROBE) { + /* + * All of the URETPROBE behaviors can be tested with either + * uretprobe attached or not + */ + bool attach; +}; + +FIXTURE_VARIANT_ADD(URETPROBE, attached) { + .attach = true, +}; + +FIXTURE_VARIANT_ADD(URETPROBE, not_attached) { + .attach = false, +}; + +FIXTURE_SETUP(URETPROBE) +{ + const size_t attr_sz = sizeof(struct perf_event_attr); + struct perf_event_attr attr; + ssize_t offset; + int type, bit; + +#ifndef __NR_uretprobe + SKIP(return, "__NR_uretprobe syscall not defined"); +#endif + + if (!variant->attach) + return; + + memset(&attr, 0, attr_sz); + + type = determine_uprobe_perf_type(); + ASSERT_GE(type, 0); + bit = determine_uprobe_retprobe_bit(); + ASSERT_GE(bit, 0); + offset = get_uprobe_offset(probed); + ASSERT_GE(offset, 0); + + attr.config |= 1 << bit; + attr.size = attr_sz; + attr.type = type; + attr.config1 = ptr_to_u64("/proc/self/exe"); + attr.config2 = offset; + + self->fd = syscall(__NR_perf_event_open, &attr, + getpid() /* pid */, -1 /* cpu */, -1 /* group_fd */, + PERF_FLAG_FD_CLOEXEC); +} + +FIXTURE_TEARDOWN(URETPROBE) +{ + /* we could call close(self->fd), but we'd need extra filter for + * that and since we are calling _exit right away.. + */ +} + +static int run_probed_with_filter(struct sock_fprog *prog) +{ + if (prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0) || + seccomp(SECCOMP_SET_MODE_FILTER, 0, prog)) { + return -1; + } + + probed(); + return 0; +} + +TEST_F(URETPROBE, uretprobe_default_allow) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + +TEST_F(URETPROBE, uretprobe_default_block) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit_group, 1, 0), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + +TEST_F(URETPROBE, uretprobe_block_uretprobe_syscall) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), +#ifdef __NR_uretprobe + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 0, 1), +#endif + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + +TEST_F(URETPROBE, uretprobe_default_block_with_uretprobe_syscall) +{ + struct sock_filter filter[] = { + BPF_STMT(BPF_LD|BPF_W|BPF_ABS, + offsetof(struct seccomp_data, nr)), +#ifdef __NR_uretprobe + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_uretprobe, 2, 0), +#endif + BPF_JUMP(BPF_JMP|BPF_JEQ|BPF_K, __NR_exit_group, 1, 0), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_KILL), + BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW), + }; + struct sock_fprog prog = { + .len = (unsigned short)ARRAY_SIZE(filter), + .filter = filter, + }; + + ASSERT_EQ(0, run_probed_with_filter(&prog)); +} + /* * TODO: * - expand NNP testing diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json index d3dd65b05b5f..9044ac054167 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json +++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json @@ -94,5 +94,37 @@ "$TC qdisc del dev $DUMMY ingress", "$IP addr del 10.10.10.10/24 dev $DUMMY" ] - } + }, + { + "id": "a4b9", + "name": "Test class qlen notification", + "category": [ + "qdisc" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP link set dev $DUMMY up || true", + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: drr", + "$TC filter add dev $DUMMY parent 1: basic classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr", + "$TC qdisc add dev $DUMMY parent 1:1 handle 2: netem", + "$TC qdisc add dev $DUMMY parent 2: handle 3: drr", + "$TC filter add dev $DUMMY parent 3: basic action drop", + "$TC class add dev $DUMMY parent 3: classid 3:1 drr", + "$TC class del dev $DUMMY classid 1:1", + "$TC class add dev $DUMMY parent 1: classid 1:1 drr" + ], + "cmdUnderTest": "ping -c1 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC qdisc ls dev $DUMMY", + "matchPattern": "drr 1: root", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DUMMY root handle 1: drr", + "$IP addr del 10.10.10.10/24 dev $DUMMY" + ] + } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json index ae3d286a32b2..6f20d033670d 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json +++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/fifo.json @@ -313,6 +313,29 @@ "matchPattern": "qdisc bfifo 1: root", "matchCount": "0", "teardown": [ + ] + }, + { + "id": "d774", + "name": "Check pfifo_head_drop qdisc enqueue behaviour when limit == 0", + "category": [ + "qdisc", + "pfifo_head_drop" + ], + "plugins": { + "requires": "nsPlugin" + }, + "setup": [ + "$IP addr add 10.10.10.10/24 dev $DUMMY || true", + "$TC qdisc add dev $DUMMY root handle 1: pfifo_head_drop limit 0", + "$IP link set dev $DUMMY up || true" + ], + "cmdUnderTest": "ping -c2 -W0.01 -I $DUMMY 10.10.10.1", + "expExitCode": "1", + "verifyCmd": "$TC -s qdisc show dev $DUMMY", + "matchPattern": "dropped 2", + "matchCount": "1", + "teardown": [ ] } ] diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c index 0ea4f6813930..4d4a76532dc9 100644 --- a/tools/testing/selftests/x86/lam.c +++ b/tools/testing/selftests/x86/lam.c @@ -237,7 +237,7 @@ static uint64_t set_metadata(uint64_t src, unsigned long lam) * both pointers should point to the same address. * * @return: - * 0: value on the pointer with metadate and value on original are same + * 0: value on the pointer with metadata and value on original are same * 1: not same. */ static int handle_lam_test(void *src, unsigned int lam) diff --git a/tools/testing/vsock/util.c b/tools/testing/vsock/util.c index 7058dc614c25..de25892f865f 100644 --- a/tools/testing/vsock/util.c +++ b/tools/testing/vsock/util.c @@ -96,41 +96,57 @@ void vsock_wait_remote_close(int fd) close(epollfd); } -/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */ -int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type) +/* Create socket <type>, bind to <cid, port> and return the file descriptor. */ +int vsock_bind(unsigned int cid, unsigned int port, int type) { - struct sockaddr_vm sa_client = { - .svm_family = AF_VSOCK, - .svm_cid = VMADDR_CID_ANY, - .svm_port = bind_port, - }; - struct sockaddr_vm sa_server = { + struct sockaddr_vm sa = { .svm_family = AF_VSOCK, .svm_cid = cid, .svm_port = port, }; + int fd; - int client_fd, ret; - - client_fd = socket(AF_VSOCK, type, 0); - if (client_fd < 0) { + fd = socket(AF_VSOCK, type, 0); + if (fd < 0) { perror("socket"); exit(EXIT_FAILURE); } - if (bind(client_fd, (struct sockaddr *)&sa_client, sizeof(sa_client))) { + if (bind(fd, (struct sockaddr *)&sa, sizeof(sa))) { perror("bind"); exit(EXIT_FAILURE); } + return fd; +} + +int vsock_connect_fd(int fd, unsigned int cid, unsigned int port) +{ + struct sockaddr_vm sa = { + .svm_family = AF_VSOCK, + .svm_cid = cid, + .svm_port = port, + }; + int ret; + timeout_begin(TIMEOUT); do { - ret = connect(client_fd, (struct sockaddr *)&sa_server, sizeof(sa_server)); + ret = connect(fd, (struct sockaddr *)&sa, sizeof(sa)); timeout_check("connect"); } while (ret < 0 && errno == EINTR); timeout_end(); - if (ret < 0) { + return ret; +} + +/* Bind to <bind_port>, connect to <cid, port> and return the file descriptor. */ +int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type) +{ + int client_fd; + + client_fd = vsock_bind(VMADDR_CID_ANY, bind_port, type); + + if (vsock_connect_fd(client_fd, cid, port)) { perror("connect"); exit(EXIT_FAILURE); } @@ -141,17 +157,6 @@ int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_po /* Connect to <cid, port> and return the file descriptor. */ int vsock_connect(unsigned int cid, unsigned int port, int type) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = port, - .svm_cid = cid, - }, - }; - int ret; int fd; control_expectln("LISTENING"); @@ -162,20 +167,14 @@ int vsock_connect(unsigned int cid, unsigned int port, int type) exit(EXIT_FAILURE); } - timeout_begin(TIMEOUT); - do { - ret = connect(fd, &addr.sa, sizeof(addr.svm)); - timeout_check("connect"); - } while (ret < 0 && errno == EINTR); - timeout_end(); - - if (ret < 0) { + if (vsock_connect_fd(fd, cid, port)) { int old_errno = errno; close(fd); fd = -1; errno = old_errno; } + return fd; } @@ -192,28 +191,9 @@ int vsock_seqpacket_connect(unsigned int cid, unsigned int port) /* Listen on <cid, port> and return the file descriptor. */ static int vsock_listen(unsigned int cid, unsigned int port, int type) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = port, - .svm_cid = cid, - }, - }; int fd; - fd = socket(AF_VSOCK, type, 0); - if (fd < 0) { - perror("socket"); - exit(EXIT_FAILURE); - } - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } + fd = vsock_bind(cid, port, type); if (listen(fd, 1) < 0) { perror("listen"); diff --git a/tools/testing/vsock/util.h b/tools/testing/vsock/util.h index e62f46b2b92a..d1f765ce3eee 100644 --- a/tools/testing/vsock/util.h +++ b/tools/testing/vsock/util.h @@ -39,10 +39,12 @@ struct test_case { void init_signals(void); unsigned int parse_cid(const char *str); unsigned int parse_port(const char *str); +int vsock_connect_fd(int fd, unsigned int cid, unsigned int port); int vsock_connect(unsigned int cid, unsigned int port, int type); int vsock_accept(unsigned int cid, unsigned int port, struct sockaddr_vm *clientaddrp, int type); int vsock_stream_connect(unsigned int cid, unsigned int port); +int vsock_bind(unsigned int cid, unsigned int port, int type); int vsock_bind_connect(unsigned int cid, unsigned int port, unsigned int bind_port, int type); int vsock_seqpacket_connect(unsigned int cid, unsigned int port); diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c index 1eebbc0d5f61..d0f6d253ac72 100644 --- a/tools/testing/vsock/vsock_test.c +++ b/tools/testing/vsock/vsock_test.c @@ -113,24 +113,9 @@ static void test_stream_bind_only_client(const struct test_opts *opts) static void test_stream_bind_only_server(const struct test_opts *opts) { - union { - struct sockaddr sa; - struct sockaddr_vm svm; - } addr = { - .svm = { - .svm_family = AF_VSOCK, - .svm_port = opts->peer_port, - .svm_cid = VMADDR_CID_ANY, - }, - }; int fd; - fd = socket(AF_VSOCK, SOCK_STREAM, 0); - - if (bind(fd, &addr.sa, sizeof(addr.svm)) < 0) { - perror("bind"); - exit(EXIT_FAILURE); - } + fd = vsock_bind(VMADDR_CID_ANY, opts->peer_port, SOCK_STREAM); /* Notify the client that the server is ready */ control_writeln("BIND"); @@ -1708,6 +1693,137 @@ static void test_stream_msgzcopy_leak_zcskb_server(const struct test_opts *opts) close(fd); } +#define MAX_PORT_RETRIES 24 /* net/vmw_vsock/af_vsock.c */ + +/* Test attempts to trigger a transport release for an unbound socket. This can + * lead to a reference count mishandling. + */ +static void test_stream_transport_uaf_client(const struct test_opts *opts) +{ + int sockets[MAX_PORT_RETRIES]; + struct sockaddr_vm addr; + int fd, i, alen; + + fd = vsock_bind(VMADDR_CID_ANY, VMADDR_PORT_ANY, SOCK_STREAM); + + alen = sizeof(addr); + if (getsockname(fd, (struct sockaddr *)&addr, &alen)) { + perror("getsockname"); + exit(EXIT_FAILURE); + } + + for (i = 0; i < MAX_PORT_RETRIES; ++i) + sockets[i] = vsock_bind(VMADDR_CID_ANY, ++addr.svm_port, + SOCK_STREAM); + + close(fd); + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + if (!vsock_connect_fd(fd, addr.svm_cid, addr.svm_port)) { + perror("Unexpected connect() #1 success"); + exit(EXIT_FAILURE); + } + + /* Vulnerable system may crash now. */ + if (!vsock_connect_fd(fd, VMADDR_CID_HOST, VMADDR_PORT_ANY)) { + perror("Unexpected connect() #2 success"); + exit(EXIT_FAILURE); + } + + close(fd); + while (i--) + close(sockets[i]); + + control_writeln("DONE"); +} + +static void test_stream_transport_uaf_server(const struct test_opts *opts) +{ + control_expectln("DONE"); +} + +static void test_stream_connect_retry_client(const struct test_opts *opts) +{ + int fd; + + fd = socket(AF_VSOCK, SOCK_STREAM, 0); + if (fd < 0) { + perror("socket"); + exit(EXIT_FAILURE); + } + + if (!vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) { + fprintf(stderr, "Unexpected connect() #1 success\n"); + exit(EXIT_FAILURE); + } + + control_writeln("LISTEN"); + control_expectln("LISTENING"); + + if (vsock_connect_fd(fd, opts->peer_cid, opts->peer_port)) { + perror("connect() #2"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_connect_retry_server(const struct test_opts *opts) +{ + int fd; + + control_expectln("LISTEN"); + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + vsock_wait_remote_close(fd); + close(fd); +} + +static void test_stream_linger_client(const struct test_opts *opts) +{ + struct linger optval = { + .l_onoff = 1, + .l_linger = 1 + }; + int fd; + + fd = vsock_stream_connect(opts->peer_cid, opts->peer_port); + if (fd < 0) { + perror("connect"); + exit(EXIT_FAILURE); + } + + if (setsockopt(fd, SOL_SOCKET, SO_LINGER, &optval, sizeof(optval))) { + perror("setsockopt(SO_LINGER)"); + exit(EXIT_FAILURE); + } + + close(fd); +} + +static void test_stream_linger_server(const struct test_opts *opts) +{ + int fd; + + fd = vsock_stream_accept(VMADDR_CID_ANY, opts->peer_port, NULL); + if (fd < 0) { + perror("accept"); + exit(EXIT_FAILURE); + } + + vsock_wait_remote_close(fd); + close(fd); +} + static struct test_case test_cases[] = { { .name = "SOCK_STREAM connection reset", @@ -1853,6 +1969,21 @@ static struct test_case test_cases[] = { .run_client = test_stream_msgzcopy_leak_zcskb_client, .run_server = test_stream_msgzcopy_leak_zcskb_server, }, + { + .name = "SOCK_STREAM transport release use-after-free", + .run_client = test_stream_transport_uaf_client, + .run_server = test_stream_transport_uaf_server, + }, + { + .name = "SOCK_STREAM retry failed connect()", + .run_client = test_stream_connect_retry_client, + .run_server = test_stream_connect_retry_server, + }, + { + .name = "SOCK_STREAM SO_LINGER null-ptr-deref", + .run_client = test_stream_linger_client, + .run_server = test_stream_linger_server, + }, {}, }; |