diff options
Diffstat (limited to 'tools')
24 files changed, 447 insertions, 135 deletions
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile index d8fe29fc19a4..8bd960658463 100644 --- a/tools/lib/api/Makefile +++ b/tools/lib/api/Makefile @@ -16,7 +16,7 @@ MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libapi.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -Werror -O6 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC CFLAGS += -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64 RM = rm -f diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile index 0c356fb65022..18ffccf00426 100644 --- a/tools/lib/lockdep/Makefile +++ b/tools/lib/lockdep/Makefile @@ -14,9 +14,10 @@ define allow-override $(eval $(1) = $(2))) endef -# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix. +# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix. $(call allow-override,CC,$(CROSS_COMPILE)gcc) $(call allow-override,AR,$(CROSS_COMPILE)ar) +$(call allow-override,LD,$(CROSS_COMPILE)ld) INSTALL = install diff --git a/tools/lib/lockdep/uinclude/linux/kernel.h b/tools/lib/lockdep/uinclude/linux/kernel.h index a11e3c357be7..cd2cc59a5da7 100644 --- a/tools/lib/lockdep/uinclude/linux/kernel.h +++ b/tools/lib/lockdep/uinclude/linux/kernel.h @@ -28,6 +28,9 @@ #define __init #define noinline #define list_add_tail_rcu list_add_tail +#define list_for_each_entry_rcu list_for_each_entry +#define barrier() +#define synchronize_sched() #ifndef CALLER_ADDR0 #define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0)) diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c index e0917c0f5d9f..29f94f6f0d9e 100644 --- a/tools/lib/traceevent/event-parse.c +++ b/tools/lib/traceevent/event-parse.c @@ -3865,7 +3865,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size, } else if (el_size == 4) { trace_seq_printf(s, "%u", *(uint32_t *)num); } else if (el_size == 8) { - trace_seq_printf(s, "%lu", *(uint64_t *)num); + trace_seq_printf(s, "%"PRIu64, *(uint64_t *)num); } else { trace_seq_printf(s, "BAD SIZE:%d 0x%x", el_size, *(uint8_t *)num); diff --git a/tools/net/bpf_jit_disasm.c b/tools/net/bpf_jit_disasm.c index c5baf9c591b7..618c2bcd4eab 100644 --- a/tools/net/bpf_jit_disasm.c +++ b/tools/net/bpf_jit_disasm.c @@ -123,6 +123,8 @@ static int get_last_jit_image(char *haystack, size_t hlen, assert(ret == 0); ptr = haystack; + memset(pmatch, 0, sizeof(pmatch)); + while (1) { ret = regexec(®ex, ptr, 1, pmatch, 0); if (ret == 0) { diff --git a/tools/perf/Makefile b/tools/perf/Makefile index c699dc35eef9..d31a7bbd7cee 100644 --- a/tools/perf/Makefile +++ b/tools/perf/Makefile @@ -24,7 +24,7 @@ unexport MAKEFLAGS # (To override it, run 'make JOBS=1' and similar.) # ifeq ($(JOBS),) - JOBS := $(shell egrep -c '^processor|^CPU' /proc/cpuinfo 2>/dev/null) + JOBS := $(shell (getconf _NPROCESSORS_ONLN || egrep -c '^processor|^CPU[0-9]' /proc/cpuinfo) 2>/dev/null) ifeq ($(JOBS),0) JOBS := 1 endif diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index bedff6b5b3cf..ad0d9b5342fb 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -132,6 +132,9 @@ int bench_futex_requeue(int argc, const char **argv, if (!fshared) futex_flag = FUTEX_PRIVATE_FLAG; + if (nrequeue > nthreads) + nrequeue = nthreads; + printf("Run summary [PID %d]: Requeuing %d threads (from [%s] %p to %p), " "%d at a time.\n\n", getpid(), nthreads, fshared ? "shared":"private", &futex1, &futex2, nrequeue); @@ -161,20 +164,18 @@ int bench_futex_requeue(int argc, const char **argv, /* Ok, all threads are patiently blocked, start requeueing */ gettimeofday(&start, NULL); - for (nrequeued = 0; nrequeued < nthreads; nrequeued += nrequeue) { + while (nrequeued < nthreads) { /* * Do not wakeup any tasks blocked on futex1, allowing * us to really measure futex_wait functionality. */ - futex_cmp_requeue(&futex1, 0, &futex2, 0, - nrequeue, futex_flag); + nrequeued += futex_cmp_requeue(&futex1, 0, &futex2, 0, + nrequeue, futex_flag); } + gettimeofday(&end, NULL); timersub(&end, &start, &runtime); - if (nrequeued > nthreads) - nrequeued = nthreads; - update_stats(&requeued_stats, nrequeued); update_stats(&requeuetime_stats, runtime.tv_usec); @@ -184,7 +185,7 @@ int bench_futex_requeue(int argc, const char **argv, } /* everybody should be blocked on futex2, wake'em up */ - nrequeued = futex_wake(&futex2, nthreads, futex_flag); + nrequeued = futex_wake(&futex2, nrequeued, futex_flag); if (nthreads != nrequeued) warnx("couldn't wakeup all tasks (%d/%d)", nrequeued, nthreads); diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index ebfa163b80b5..ba5efa4710b5 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -180,7 +180,7 @@ static const struct option options[] = { OPT_INTEGER('H', "thp" , &p0.thp, "MADV_NOHUGEPAGE < 0 < MADV_HUGEPAGE"), OPT_BOOLEAN('c', "show_convergence", &p0.show_convergence, "show convergence details"), OPT_BOOLEAN('m', "measure_convergence", &p0.measure_convergence, "measure convergence latency"), - OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "bzero the initial allocations"), + OPT_BOOLEAN('q', "quiet" , &p0.show_quiet, "quiet mode"), OPT_BOOLEAN('S', "serialize-startup", &p0.serialize_startup,"serialize thread startup"), /* Special option string parsing callbacks: */ @@ -828,6 +828,9 @@ static int count_process_nodes(int process_nr) td = g->threads + task_nr; node = numa_node_of_cpu(td->curr_cpu); + if (node < 0) /* curr_cpu was likely still -1 */ + return 0; + node_present[node] = 1; } @@ -882,6 +885,11 @@ static void calc_convergence_compression(int *strong) for (p = 0; p < g->p.nr_proc; p++) { unsigned int nodes = count_process_nodes(p); + if (!nodes) { + *strong = 0; + return; + } + nodes_min = min(nodes, nodes_min); nodes_max = max(nodes, nodes_max); } @@ -1395,7 +1403,7 @@ static void print_res(const char *name, double val, if (!name) name = "main,"; - if (g->p.show_quiet) + if (!g->p.show_quiet) printf(" %-30s %15.3f, %-15s %s\n", name, val, txt_unit, txt_short); else printf(" %14.3f %s\n", val, txt_long); diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c index 63ea01349b6e..1634186d537c 100644 --- a/tools/perf/builtin-kmem.c +++ b/tools/perf/builtin-kmem.c @@ -319,7 +319,7 @@ static int page_stat_cmp(struct page_stat *a, struct page_stat *b) return 0; } -static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool create) +static struct page_stat *search_page_alloc_stat(struct page_stat *pstat, bool create) { struct rb_node **node = &page_alloc_tree.rb_node; struct rb_node *parent = NULL; @@ -331,7 +331,7 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre parent = *node; data = rb_entry(*node, struct page_stat, node); - cmp = page_stat_cmp(data, stat); + cmp = page_stat_cmp(data, pstat); if (cmp < 0) node = &parent->rb_left; else if (cmp > 0) @@ -345,10 +345,10 @@ static struct page_stat *search_page_alloc_stat(struct page_stat *stat, bool cre data = zalloc(sizeof(*data)); if (data != NULL) { - data->page = stat->page; - data->order = stat->order; - data->gfp_flags = stat->gfp_flags; - data->migrate_type = stat->migrate_type; + data->page = pstat->page; + data->order = pstat->order; + data->gfp_flags = pstat->gfp_flags; + data->migrate_type = pstat->migrate_type; rb_link_node(&data->node, parent, node); rb_insert_color(&data->node, &page_alloc_tree); @@ -375,7 +375,7 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel, unsigned int migrate_type = perf_evsel__intval(evsel, sample, "migratetype"); u64 bytes = kmem_page_size << order; - struct page_stat *stat; + struct page_stat *pstat; struct page_stat this = { .order = order, .gfp_flags = gfp_flags, @@ -401,21 +401,21 @@ static int perf_evsel__process_page_alloc_event(struct perf_evsel *evsel, * This is to find the current page (with correct gfp flags and * migrate type) at free event. */ - stat = search_page(page, true); - if (stat == NULL) + pstat = search_page(page, true); + if (pstat == NULL) return -ENOMEM; - stat->order = order; - stat->gfp_flags = gfp_flags; - stat->migrate_type = migrate_type; + pstat->order = order; + pstat->gfp_flags = gfp_flags; + pstat->migrate_type = migrate_type; this.page = page; - stat = search_page_alloc_stat(&this, true); - if (stat == NULL) + pstat = search_page_alloc_stat(&this, true); + if (pstat == NULL) return -ENOMEM; - stat->nr_alloc++; - stat->alloc_bytes += bytes; + pstat->nr_alloc++; + pstat->alloc_bytes += bytes; order_stats[order][migrate_type]++; @@ -428,7 +428,7 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel, u64 page; unsigned int order = perf_evsel__intval(evsel, sample, "order"); u64 bytes = kmem_page_size << order; - struct page_stat *stat; + struct page_stat *pstat; struct page_stat this = { .order = order, }; @@ -441,8 +441,8 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel, nr_page_frees++; total_page_free_bytes += bytes; - stat = search_page(page, false); - if (stat == NULL) { + pstat = search_page(page, false); + if (pstat == NULL) { pr_debug2("missing free at page %"PRIx64" (order: %d)\n", page, order); @@ -453,18 +453,18 @@ static int perf_evsel__process_page_free_event(struct perf_evsel *evsel, } this.page = page; - this.gfp_flags = stat->gfp_flags; - this.migrate_type = stat->migrate_type; + this.gfp_flags = pstat->gfp_flags; + this.migrate_type = pstat->migrate_type; - rb_erase(&stat->node, &page_tree); - free(stat); + rb_erase(&pstat->node, &page_tree); + free(pstat); - stat = search_page_alloc_stat(&this, false); - if (stat == NULL) + pstat = search_page_alloc_stat(&this, false); + if (pstat == NULL) return -ENOENT; - stat->nr_free++; - stat->free_bytes += bytes; + pstat->nr_free++; + pstat->free_bytes += bytes; return 0; } @@ -640,9 +640,9 @@ static void print_page_summary(void) nr_page_frees, total_page_free_bytes / 1024); printf("\n"); - printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests", + printf("%-30s: %'16"PRIu64" [ %'16"PRIu64" KB ]\n", "Total alloc+freed requests", nr_alloc_freed, (total_alloc_freed_bytes) / 1024); - printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total alloc-only requests", + printf("%-30s: %'16"PRIu64" [ %'16"PRIu64" KB ]\n", "Total alloc-only requests", nr_page_allocs - nr_alloc_freed, (total_page_alloc_bytes - total_alloc_freed_bytes) / 1024); printf("%-30s: %'16lu [ %'16"PRIu64" KB ]\n", "Total free-only requests", diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 476cdf7afcca..b63aeda719be 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -329,7 +329,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist, fprintf(stdout, "\n\n"); } - if (sort_order == default_sort_order && + if (sort_order == NULL && parent_pattern == default_parent_pattern) { fprintf(stdout, "#\n# (%s)\n#\n", help); diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index 1cb3436276d1..6a4d5d41c671 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -733,7 +733,7 @@ static void perf_event__process_sample(struct perf_tool *tool, "Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n" "Check /proc/sys/kernel/kptr_restrict.\n\n" "Kernel%s samples will not be resolved.\n", - !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ? + al.map && !RB_EMPTY_ROOT(&al.map->dso->symbols[MAP__FUNCTION]) ? " modules" : ""); if (use_browser <= 0) sleep(5); diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c index e124741be187..e122970361f2 100644 --- a/tools/perf/builtin-trace.c +++ b/tools/perf/builtin-trace.c @@ -2241,10 +2241,11 @@ static int trace__run(struct trace *trace, int argc, const char **argv) if (err < 0) goto out_error_mmap; + if (!target__none(&trace->opts.target)) + perf_evlist__enable(evlist); + if (forks) perf_evlist__start_workload(evlist); - else - perf_evlist__enable(evlist); trace->multiple_threads = evlist->threads->map[0] == -1 || evlist->threads->nr > 1 || @@ -2272,6 +2273,11 @@ next_event: if (interrupted) goto out_disable; + + if (done && !draining) { + perf_evlist__disable(evlist); + draining = true; + } } } diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c index d8bb616ff57c..d05b77cf35f7 100644 --- a/tools/perf/util/probe-event.c +++ b/tools/perf/util/probe-event.c @@ -1084,6 +1084,8 @@ static int parse_perf_probe_point(char *arg, struct perf_probe_event *pev) * * TODO:Group name support */ + if (!arg) + return -EINVAL; ptr = strpbrk(arg, ";=@+%"); if (ptr && *ptr == '=') { /* Event name */ diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c index b5bf9d5efeaf..2a76e14db732 100644 --- a/tools/perf/util/probe-finder.c +++ b/tools/perf/util/probe-finder.c @@ -578,10 +578,12 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf) /* Search child die for local variables and parameters. */ if (!die_find_variable_at(sc_die, pf->pvar->var, pf->addr, &vr_die)) { /* Search again in global variables */ - if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die)) + if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, + 0, &vr_die)) { pr_warning("Failed to find '%s' in this function.\n", pf->pvar->var); ret = -ENOENT; + } } if (ret >= 0) ret = convert_variable(&vr_die, pf); diff --git a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c index 90a8c4f071e7..c83f1606970b 100644 --- a/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c +++ b/tools/power/cpupower/utils/idle_monitor/mperf_monitor.c @@ -135,7 +135,7 @@ static int mperf_get_count_percent(unsigned int id, double *percent, dprint("%s: TSC Ref - mperf_diff: %llu, tsc_diff: %llu\n", mperf_cstates[id].name, mperf_diff, tsc_diff); } else if (max_freq_mode == MAX_FREQ_SYSFS) { - timediff = timespec_diff_us(time_start, time_end); + timediff = max_frequency * timespec_diff_us(time_start, time_end); *percent = 100.0 * mperf_diff / timediff; dprint("%s: MAXFREQ - mperf_diff: %llu, time_diff: %llu\n", mperf_cstates[id].name, mperf_diff, timediff); @@ -176,7 +176,7 @@ static int mperf_get_count_freq(unsigned int id, unsigned long long *count, dprint("%s: Average freq based on %s maximum frequency:\n", mperf_cstates[id].name, (max_freq_mode == MAX_FREQ_TSC_REF) ? "TSC calculated" : "sysfs read"); - dprint("%max_frequency: %lu", max_frequency); + dprint("max_frequency: %lu\n", max_frequency); dprint("aperf_diff: %llu\n", aperf_diff); dprint("mperf_diff: %llu\n", mperf_diff); dprint("avg freq: %llu\n", *count); @@ -279,6 +279,7 @@ use_sysfs: return -1; } max_freq_mode = MAX_FREQ_SYSFS; + max_frequency /= 1000; /* Default automatically to MHz value */ return 0; } diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c index bac98ca3d4ca..323b65edfc97 100644 --- a/tools/power/x86/turbostat/turbostat.c +++ b/tools/power/x86/turbostat/turbostat.c @@ -52,6 +52,7 @@ unsigned int skip_c0; unsigned int skip_c1; unsigned int do_nhm_cstates; unsigned int do_snb_cstates; +unsigned int do_knl_cstates; unsigned int do_pc2; unsigned int do_pc3; unsigned int do_pc6; @@ -91,6 +92,7 @@ unsigned int do_gfx_perf_limit_reasons; unsigned int do_ring_perf_limit_reasons; unsigned int crystal_hz; unsigned long long tsc_hz; +int base_cpu; #define RAPL_PKG (1 << 0) /* 0x610 MSR_PKG_POWER_LIMIT */ @@ -316,7 +318,7 @@ void print_header(void) if (do_nhm_cstates) outp += sprintf(outp, " CPU%%c1"); - if (do_nhm_cstates && !do_slm_cstates) + if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) outp += sprintf(outp, " CPU%%c3"); if (do_nhm_cstates) outp += sprintf(outp, " CPU%%c6"); @@ -546,7 +548,7 @@ int format_counters(struct thread_data *t, struct core_data *c, if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) goto done; - if (do_nhm_cstates && !do_slm_cstates) + if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) outp += sprintf(outp, "%8.2f", 100.0 * c->c3/t->tsc); if (do_nhm_cstates) outp += sprintf(outp, "%8.2f", 100.0 * c->c6/t->tsc); @@ -1018,14 +1020,17 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (!(t->flags & CPU_IS_FIRST_THREAD_IN_CORE)) return 0; - if (do_nhm_cstates && !do_slm_cstates) { + if (do_nhm_cstates && !do_slm_cstates && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C3_RESIDENCY, &c->c3)) return -6; } - if (do_nhm_cstates) { + if (do_nhm_cstates && !do_knl_cstates) { if (get_msr(cpu, MSR_CORE_C6_RESIDENCY, &c->c6)) return -7; + } else if (do_knl_cstates) { + if (get_msr(cpu, MSR_KNL_CORE_C6_RESIDENCY, &c->c6)) + return -7; } if (do_snb_cstates) @@ -1150,7 +1155,7 @@ dump_nhm_platform_info(void) unsigned long long msr; unsigned int ratio; - get_msr(0, MSR_NHM_PLATFORM_INFO, &msr); + get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr); fprintf(stderr, "cpu0: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", msr); @@ -1162,7 +1167,7 @@ dump_nhm_platform_info(void) fprintf(stderr, "%d * %.0f = %.0f MHz base frequency\n", ratio, bclk, ratio * bclk); - get_msr(0, MSR_IA32_POWER_CTL, &msr); + get_msr(base_cpu, MSR_IA32_POWER_CTL, &msr); fprintf(stderr, "cpu0: MSR_IA32_POWER_CTL: 0x%08llx (C1E auto-promotion: %sabled)\n", msr, msr & 0x2 ? "EN" : "DIS"); @@ -1175,7 +1180,7 @@ dump_hsw_turbo_ratio_limits(void) unsigned long long msr; unsigned int ratio; - get_msr(0, MSR_TURBO_RATIO_LIMIT2, &msr); + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT2, &msr); fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT2: 0x%08llx\n", msr); @@ -1197,7 +1202,7 @@ dump_ivt_turbo_ratio_limits(void) unsigned long long msr; unsigned int ratio; - get_msr(0, MSR_TURBO_RATIO_LIMIT1, &msr); + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT1, &msr); fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT1: 0x%08llx\n", msr); @@ -1249,7 +1254,7 @@ dump_nhm_turbo_ratio_limits(void) unsigned long long msr; unsigned int ratio; - get_msr(0, MSR_TURBO_RATIO_LIMIT, &msr); + get_msr(base_cpu, MSR_TURBO_RATIO_LIMIT, &msr); fprintf(stderr, "cpu0: MSR_TURBO_RATIO_LIMIT: 0x%08llx\n", msr); @@ -1296,11 +1301,72 @@ dump_nhm_turbo_ratio_limits(void) } static void +dump_knl_turbo_ratio_limits(void) +{ + int cores; + unsigned int ratio; + unsigned long long msr; + int delta_cores; + int delta_ratio; + int i; + + get_msr(base_cpu, MSR_NHM_TURBO_RATIO_LIMIT, &msr); + + fprintf(stderr, "cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n", + msr); + + /** + * Turbo encoding in KNL is as follows: + * [7:0] -- Base value of number of active cores of bucket 1. + * [15:8] -- Base value of freq ratio of bucket 1. + * [20:16] -- +ve delta of number of active cores of bucket 2. + * i.e. active cores of bucket 2 = + * active cores of bucket 1 + delta + * [23:21] -- Negative delta of freq ratio of bucket 2. + * i.e. freq ratio of bucket 2 = + * freq ratio of bucket 1 - delta + * [28:24]-- +ve delta of number of active cores of bucket 3. + * [31:29]-- -ve delta of freq ratio of bucket 3. + * [36:32]-- +ve delta of number of active cores of bucket 4. + * [39:37]-- -ve delta of freq ratio of bucket 4. + * [44:40]-- +ve delta of number of active cores of bucket 5. + * [47:45]-- -ve delta of freq ratio of bucket 5. + * [52:48]-- +ve delta of number of active cores of bucket 6. + * [55:53]-- -ve delta of freq ratio of bucket 6. + * [60:56]-- +ve delta of number of active cores of bucket 7. + * [63:61]-- -ve delta of freq ratio of bucket 7. + */ + cores = msr & 0xFF; + ratio = (msr >> 8) && 0xFF; + if (ratio > 0) + fprintf(stderr, + "%d * %.0f = %.0f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, cores); + + for (i = 16; i < 64; i = i + 8) { + delta_cores = (msr >> i) & 0x1F; + delta_ratio = (msr >> (i + 5)) && 0x7; + if (!delta_cores || !delta_ratio) + return; + cores = cores + delta_cores; + ratio = ratio - delta_ratio; + + /** -ve ratios will make successive ratio calculations + * negative. Hence return instead of carrying on. + */ + if (ratio > 0) + fprintf(stderr, + "%d * %.0f = %.0f MHz max turbo %d active cores\n", + ratio, bclk, ratio * bclk, cores); + } +} + +static void dump_nhm_cst_cfg(void) { unsigned long long msr; - get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); + get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); #define SNB_C1_AUTO_UNDEMOTE (1UL << 27) #define SNB_C3_AUTO_UNDEMOTE (1UL << 28) @@ -1381,12 +1447,41 @@ int parse_int_file(const char *fmt, ...) } /* - * cpu_is_first_sibling_in_core(cpu) - * return 1 if given CPU is 1st HT sibling in the core + * get_cpu_position_in_core(cpu) + * return the position of the CPU among its HT siblings in the core + * return -1 if the sibling is not in list */ -int cpu_is_first_sibling_in_core(int cpu) +int get_cpu_position_in_core(int cpu) { - return cpu == parse_int_file("/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu); + char path[64]; + FILE *filep; + int this_cpu; + char character; + int i; + + sprintf(path, + "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", + cpu); + filep = fopen(path, "r"); + if (filep == NULL) { + perror(path); + exit(1); + } + + for (i = 0; i < topo.num_threads_per_core; i++) { + fscanf(filep, "%d", &this_cpu); + if (this_cpu == cpu) { + fclose(filep); + return i; + } + + /* Account for no separator after last thread*/ + if (i != (topo.num_threads_per_core - 1)) + fscanf(filep, "%c", &character); + } + + fclose(filep); + return -1; } /* @@ -1412,25 +1507,31 @@ int get_num_ht_siblings(int cpu) { char path[80]; FILE *filep; - int sib1, sib2; - int matches; + int sib1; + int matches = 0; char character; + char str[100]; + char *ch; sprintf(path, "/sys/devices/system/cpu/cpu%d/topology/thread_siblings_list", cpu); filep = fopen_or_die(path, "r"); + /* * file format: - * if a pair of number with a character between: 2 siblings (eg. 1-2, or 1,4) - * otherwinse 1 sibling (self). + * A ',' separated or '-' separated set of numbers + * (eg 1-2 or 1,3,4,5) */ - matches = fscanf(filep, "%d%c%d\n", &sib1, &character, &sib2); + fscanf(filep, "%d%c\n", &sib1, &character); + fseek(filep, 0, SEEK_SET); + fgets(str, 100, filep); + ch = strchr(str, character); + while (ch != NULL) { + matches++; + ch = strchr(ch+1, character); + } fclose(filep); - - if (matches == 3) - return 2; - else - return 1; + return matches+1; } /* @@ -1594,8 +1695,10 @@ restart: void check_dev_msr() { struct stat sb; + char pathname[32]; - if (stat("/dev/cpu/0/msr", &sb)) + sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); + if (stat(pathname, &sb)) if (system("/sbin/modprobe msr > /dev/null 2>&1")) err(-5, "no /dev/cpu/0/msr, Try \"# modprobe msr\" "); } @@ -1608,6 +1711,7 @@ void check_permissions() cap_user_data_t cap_data = &cap_data_data; extern int capget(cap_user_header_t hdrp, cap_user_data_t datap); int do_exit = 0; + char pathname[32]; /* check for CAP_SYS_RAWIO */ cap_header->pid = getpid(); @@ -1622,7 +1726,8 @@ void check_permissions() } /* test file permissions */ - if (euidaccess("/dev/cpu/0/msr", R_OK)) { + sprintf(pathname, "/dev/cpu/%d/msr", base_cpu); + if (euidaccess(pathname, R_OK)) { do_exit++; warn("/dev/cpu/0/msr open failed, try chown or chmod +r /dev/cpu/*/msr"); } @@ -1704,7 +1809,7 @@ int probe_nhm_msrs(unsigned int family, unsigned int model) default: return 0; } - get_msr(0, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); + get_msr(base_cpu, MSR_NHM_SNB_PKG_CST_CFG_CTL, &msr); pkg_cstate_limit = pkg_cstate_limits[msr & 0xF]; @@ -1753,6 +1858,21 @@ int has_hsw_turbo_ratio_limit(unsigned int family, unsigned int model) } } +int has_knl_turbo_ratio_limit(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + + if (family != 6) + return 0; + + switch (model) { + case 0x57: /* Knights Landing */ + return 1; + default: + return 0; + } +} static void dump_cstate_pstate_config_info(family, model) { @@ -1770,6 +1890,9 @@ dump_cstate_pstate_config_info(family, model) if (has_nhm_turbo_ratio_limit(family, model)) dump_nhm_turbo_ratio_limits(); + if (has_knl_turbo_ratio_limit(family, model)) + dump_knl_turbo_ratio_limits(); + dump_nhm_cst_cfg(); } @@ -1801,7 +1924,7 @@ int print_epb(struct thread_data *t, struct core_data *c, struct pkg_data *p) if (get_msr(cpu, MSR_IA32_ENERGY_PERF_BIAS, &msr)) return 0; - switch (msr & 0x7) { + switch (msr & 0xF) { case ENERGY_PERF_BIAS_PERFORMANCE: epb_string = "performance"; break; @@ -1925,7 +2048,7 @@ double get_tdp(model) unsigned long long msr; if (do_rapl & RAPL_PKG_POWER_INFO) - if (!get_msr(0, MSR_PKG_POWER_INFO, &msr)) + if (!get_msr(base_cpu, MSR_PKG_POWER_INFO, &msr)) return ((msr >> 0) & RAPL_POWER_GRANULARITY) * rapl_power_units; switch (model) { @@ -1950,6 +2073,7 @@ rapl_dram_energy_units_probe(int model, double rapl_energy_units) case 0x3F: /* HSX */ case 0x4F: /* BDX */ case 0x56: /* BDX-DE */ + case 0x57: /* KNL */ return (rapl_dram_energy_units = 15.3 / 1000000); default: return (rapl_energy_units); @@ -1991,6 +2115,7 @@ void rapl_probe(unsigned int family, unsigned int model) case 0x3F: /* HSX */ case 0x4F: /* BDX */ case 0x56: /* BDX-DE */ + case 0x57: /* KNL */ do_rapl = RAPL_PKG | RAPL_DRAM | RAPL_DRAM_POWER_INFO | RAPL_DRAM_PERF_STATUS | RAPL_PKG_PERF_STATUS | RAPL_PKG_POWER_INFO; break; case 0x2D: @@ -2006,7 +2131,7 @@ void rapl_probe(unsigned int family, unsigned int model) } /* units on package 0, verify later other packages match */ - if (get_msr(0, MSR_RAPL_POWER_UNIT, &msr)) + if (get_msr(base_cpu, MSR_RAPL_POWER_UNIT, &msr)) return; rapl_power_units = 1.0 / (1 << (msr & 0xF)); @@ -2331,6 +2456,17 @@ int is_slm(unsigned int family, unsigned int model) return 0; } +int is_knl(unsigned int family, unsigned int model) +{ + if (!genuine_intel) + return 0; + switch (model) { + case 0x57: /* KNL */ + return 1; + } + return 0; +} + #define SLM_BCLK_FREQS 5 double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0}; @@ -2340,7 +2476,7 @@ double slm_bclk(void) unsigned int i; double freq; - if (get_msr(0, MSR_FSB_FREQ, &msr)) + if (get_msr(base_cpu, MSR_FSB_FREQ, &msr)) fprintf(stderr, "SLM BCLK: unknown\n"); i = msr & 0xf; @@ -2408,7 +2544,7 @@ int set_temperature_target(struct thread_data *t, struct core_data *c, struct pk if (!do_nhm_platform_info) goto guess; - if (get_msr(0, MSR_IA32_TEMPERATURE_TARGET, &msr)) + if (get_msr(base_cpu, MSR_IA32_TEMPERATURE_TARGET, &msr)) goto guess; target_c_local = (msr >> 16) & 0xFF; @@ -2541,6 +2677,7 @@ void process_cpuid() do_c8_c9_c10 = has_hsw_msrs(family, model); do_skl_residency = has_skl_msrs(family, model); do_slm_cstates = is_slm(family, model); + do_knl_cstates = is_knl(family, model); bclk = discover_bclk(family, model); rapl_probe(family, model); @@ -2755,13 +2892,9 @@ int initialize_counters(int cpu_id) my_package_id = get_physical_package_id(cpu_id); my_core_id = get_core_id(cpu_id); - - if (cpu_is_first_sibling_in_core(cpu_id)) { - my_thread_id = 0; + my_thread_id = get_cpu_position_in_core(cpu_id); + if (!my_thread_id) topo.num_cores++; - } else { - my_thread_id = 1; - } init_counter(EVEN_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id); init_counter(ODD_COUNTERS, my_thread_id, my_core_id, my_package_id, cpu_id); @@ -2785,13 +2918,24 @@ void setup_all_buffers(void) for_all_proc_cpus(initialize_counters); } +void set_base_cpu(void) +{ + base_cpu = sched_getcpu(); + if (base_cpu < 0) + err(-ENODEV, "No valid cpus found"); + + if (debug > 1) + fprintf(stderr, "base_cpu = %d\n", base_cpu); +} + void turbostat_init() { + setup_all_buffers(); + set_base_cpu(); check_dev_msr(); check_permissions(); process_cpuid(); - setup_all_buffers(); if (debug) for_all_cpus(print_epb, ODD_COUNTERS); @@ -2870,7 +3014,7 @@ int get_and_dump_counters(void) } void print_version() { - fprintf(stderr, "turbostat version 4.5 2 Apr, 2015" + fprintf(stderr, "turbostat version 4.7 27-May, 2015" " - Len Brown <lenb@kernel.org>\n"); } diff --git a/tools/testing/selftests/x86/Makefile b/tools/testing/selftests/x86/Makefile index ddf63569df5a..9b0d8baf2934 100644 --- a/tools/testing/selftests/x86/Makefile +++ b/tools/testing/selftests/x86/Makefile @@ -1,48 +1,59 @@ -.PHONY: all all_32 all_64 check_build32 clean run_tests +all: + +include ../lib.mk + +.PHONY: all all_32 all_64 warn_32bit_failure clean TARGETS_C_BOTHBITS := sigreturn single_step_syscall +TARGETS_C_32BIT_ONLY := entry_from_vm86 -BINARIES_32 := $(TARGETS_C_BOTHBITS:%=%_32) +TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY) +BINARIES_32 := $(TARGETS_C_32BIT_ALL:%=%_32) BINARIES_64 := $(TARGETS_C_BOTHBITS:%=%_64) CFLAGS := -O2 -g -std=gnu99 -pthread -Wall -UNAME_P := $(shell uname -p) +UNAME_M := $(shell uname -m) +CAN_BUILD_I386 := $(shell ./check_cc.sh $(CC) trivial_32bit_program.c -m32) +CAN_BUILD_X86_64 := $(shell ./check_cc.sh $(CC) trivial_64bit_program.c) -# Always build 32-bit tests +ifeq ($(CAN_BUILD_I386),1) all: all_32 +TEST_PROGS += $(BINARIES_32) +endif -# If we're on a 64-bit host, build 64-bit tests as well -ifeq ($(shell uname -p),x86_64) +ifeq ($(CAN_BUILD_X86_64),1) all: all_64 +TEST_PROGS += $(BINARIES_64) endif -all_32: check_build32 $(BINARIES_32) +all_32: $(BINARIES_32) all_64: $(BINARIES_64) clean: $(RM) $(BINARIES_32) $(BINARIES_64) -run_tests: - ./run_x86_tests.sh - -$(TARGETS_C_BOTHBITS:%=%_32): %_32: %.c +$(TARGETS_C_32BIT_ALL:%=%_32): %_32: %.c $(CC) -m32 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl $(TARGETS_C_BOTHBITS:%=%_64): %_64: %.c $(CC) -m64 -o $@ $(CFLAGS) $(EXTRA_CFLAGS) $^ -lrt -ldl -check_build32: - @if ! $(CC) -m32 -o /dev/null trivial_32bit_program.c; then \ - echo "Warning: you seem to have a broken 32-bit build" 2>&1; \ - echo "environment. If you are using a Debian-like"; \ - echo " distribution, try:"; \ - echo ""; \ - echo " apt-get install gcc-multilib libc6-i386 libc6-dev-i386"; \ - echo ""; \ - echo "If you are using a Fedora-like distribution, try:"; \ - echo ""; \ - echo " yum install glibc-devel.*i686"; \ - exit 1; \ - fi +# x86_64 users should be encouraged to install 32-bit libraries +ifeq ($(CAN_BUILD_I386)$(CAN_BUILD_X86_64),01) +all: warn_32bit_failure + +warn_32bit_failure: + @echo "Warning: you seem to have a broken 32-bit build" 2>&1; \ + echo "environment. This will reduce test coverage of 64-bit" 2>&1; \ + echo "kernels. If you are using a Debian-like distribution," 2>&1; \ + echo "try:"; 2>&1; \ + echo ""; \ + echo " apt-get install gcc-multilib libc6-i386 libc6-dev-i386"; \ + echo ""; \ + echo "If you are using a Fedora-like distribution, try:"; \ + echo ""; \ + echo " yum install glibc-devel.*i686"; \ + exit 0; +endif diff --git a/tools/testing/selftests/x86/check_cc.sh b/tools/testing/selftests/x86/check_cc.sh new file mode 100755 index 000000000000..172d3293fb7b --- /dev/null +++ b/tools/testing/selftests/x86/check_cc.sh @@ -0,0 +1,16 @@ +#!/bin/sh +# check_cc.sh - Helper to test userspace compilation support +# Copyright (c) 2015 Andrew Lutomirski +# GPL v2 + +CC="$1" +TESTPROG="$2" +shift 2 + +if "$CC" -o /dev/null "$TESTPROG" -O0 "$@" 2>/dev/null; then + echo 1 +else + echo 0 +fi + +exit 0 diff --git a/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c new file mode 100644 index 000000000000..5c38a187677b --- /dev/null +++ b/tools/testing/selftests/x86/entry_from_vm86.c @@ -0,0 +1,114 @@ +/* + * entry_from_vm86.c - tests kernel entries from vm86 mode + * Copyright (c) 2014-2015 Andrew Lutomirski + * + * This exercises a few paths that need to special-case vm86 mode. + * + * GPL v2. + */ + +#define _GNU_SOURCE + +#include <assert.h> +#include <stdlib.h> +#include <sys/syscall.h> +#include <sys/signal.h> +#include <sys/ucontext.h> +#include <unistd.h> +#include <stdio.h> +#include <string.h> +#include <inttypes.h> +#include <sys/mman.h> +#include <err.h> +#include <stddef.h> +#include <stdbool.h> +#include <errno.h> +#include <sys/vm86.h> + +static unsigned long load_addr = 0x10000; +static int nerrs = 0; + +asm ( + ".pushsection .rodata\n\t" + ".type vmcode_bound, @object\n\t" + "vmcode:\n\t" + "vmcode_bound:\n\t" + ".code16\n\t" + "bound %ax, (2048)\n\t" + "int3\n\t" + "vmcode_sysenter:\n\t" + "sysenter\n\t" + ".size vmcode, . - vmcode\n\t" + "end_vmcode:\n\t" + ".code32\n\t" + ".popsection" + ); + +extern unsigned char vmcode[], end_vmcode[]; +extern unsigned char vmcode_bound[], vmcode_sysenter[]; + +static void do_test(struct vm86plus_struct *v86, unsigned long eip, + const char *text) +{ + long ret; + + printf("[RUN]\t%s from vm86 mode\n", text); + v86->regs.eip = eip; + ret = vm86(VM86_ENTER, v86); + + if (ret == -1 && errno == ENOSYS) { + printf("[SKIP]\tvm86 not supported\n"); + return; + } + + if (VM86_TYPE(ret) == VM86_INTx) { + char trapname[32]; + int trapno = VM86_ARG(ret); + if (trapno == 13) + strcpy(trapname, "GP"); + else if (trapno == 5) + strcpy(trapname, "BR"); + else if (trapno == 14) + strcpy(trapname, "PF"); + else + sprintf(trapname, "%d", trapno); + + printf("[OK]\tExited vm86 mode due to #%s\n", trapname); + } else if (VM86_TYPE(ret) == VM86_UNKNOWN) { + printf("[OK]\tExited vm86 mode due to unhandled GP fault\n"); + } else { + printf("[OK]\tExited vm86 mode due to type %ld, arg %ld\n", + VM86_TYPE(ret), VM86_ARG(ret)); + } +} + +int main(void) +{ + struct vm86plus_struct v86; + unsigned char *addr = mmap((void *)load_addr, 4096, + PROT_READ | PROT_WRITE | PROT_EXEC, + MAP_ANONYMOUS | MAP_PRIVATE, -1,0); + if (addr != (unsigned char *)load_addr) + err(1, "mmap"); + + memcpy(addr, vmcode, end_vmcode - vmcode); + addr[2048] = 2; + addr[2050] = 3; + + memset(&v86, 0, sizeof(v86)); + + v86.regs.cs = load_addr / 16; + v86.regs.ss = load_addr / 16; + v86.regs.ds = load_addr / 16; + v86.regs.es = load_addr / 16; + + assert((v86.regs.cs & 3) == 0); /* Looks like RPL = 0 */ + + /* #BR -- should deliver SIG??? */ + do_test(&v86, vmcode_bound - vmcode, "#BR"); + + /* SYSENTER -- should cause #GP or #UD depending on CPU */ + do_test(&v86, vmcode_sysenter - vmcode, "SYSENTER"); + + return (nerrs == 0 ? 0 : 1); +} diff --git a/tools/testing/selftests/x86/run_x86_tests.sh b/tools/testing/selftests/x86/run_x86_tests.sh deleted file mode 100644 index 3fc19b376812..000000000000 --- a/tools/testing/selftests/x86/run_x86_tests.sh +++ /dev/null @@ -1,13 +0,0 @@ -#!/bin/bash - -# This is deliberately minimal. IMO kselftests should provide a standard -# script here. -./sigreturn_32 || exit 1 -./single_step_syscall_32 || exit 1 - -if [[ "$uname -p" -eq "x86_64" ]]; then - ./sigreturn_64 || exit 1 - ./single_step_syscall_64 || exit 1 -fi - -exit 0 diff --git a/tools/testing/selftests/x86/trivial_32bit_program.c b/tools/testing/selftests/x86/trivial_32bit_program.c index 2e231beb0a39..fabdf0f51621 100644 --- a/tools/testing/selftests/x86/trivial_32bit_program.c +++ b/tools/testing/selftests/x86/trivial_32bit_program.c @@ -4,6 +4,10 @@ * GPL v2 */ +#ifndef __i386__ +# error wrong architecture +#endif + #include <stdio.h> int main() diff --git a/tools/testing/selftests/x86/trivial_64bit_program.c b/tools/testing/selftests/x86/trivial_64bit_program.c new file mode 100644 index 000000000000..b994946c40fb --- /dev/null +++ b/tools/testing/selftests/x86/trivial_64bit_program.c @@ -0,0 +1,18 @@ +/* + * Trivial program to check that we have a valid 32-bit build environment. + * Copyright (c) 2015 Andy Lutomirski + * GPL v2 + */ + +#ifndef __x86_64__ +# error wrong architecture +#endif + +#include <stdio.h> + +int main() +{ + printf("\n"); + + return 0; +} diff --git a/tools/thermal/tmon/Makefile b/tools/thermal/tmon/Makefile index 0788621c8d76..2e83dd3655a2 100644 --- a/tools/thermal/tmon/Makefile +++ b/tools/thermal/tmon/Makefile @@ -12,10 +12,6 @@ TARGET=tmon INSTALL_PROGRAM=install -m 755 -p DEL_FILE=rm -f -INSTALL_CONFIGFILE=install -m 644 -p -CONFIG_FILE= -CONFIG_PATH= - # Static builds might require -ltinfo, for instance ifneq ($(findstring -static, $(LDFLAGS)),) STATIC := --static @@ -38,13 +34,9 @@ valgrind: tmon install: - mkdir -p $(INSTALL_ROOT)/$(BINDIR) - $(INSTALL_PROGRAM) "$(TARGET)" "$(INSTALL_ROOT)/$(BINDIR)/$(TARGET)" - - mkdir -p $(INSTALL_ROOT)/$(CONFIG_PATH) - - $(INSTALL_CONFIGFILE) "$(CONFIG_FILE)" "$(INSTALL_ROOT)/$(CONFIG_PATH)" uninstall: $(DEL_FILE) "$(INSTALL_ROOT)/$(BINDIR)/$(TARGET)" - $(CONFIG_FILE) "$(CONFIG_PATH)" - clean: find . -name "*.o" | xargs $(DEL_FILE) diff --git a/tools/vm/Makefile b/tools/vm/Makefile index ac884b65a072..93aadaf7ff63 100644 --- a/tools/vm/Makefile +++ b/tools/vm/Makefile @@ -3,7 +3,7 @@ TARGETS=page-types slabinfo page_owner_sort LIB_DIR = ../lib/api -LIBS = $(LIB_DIR)/libapikfs.a +LIBS = $(LIB_DIR)/libapi.a CC = $(CROSS_COMPILE)gcc CFLAGS = -Wall -Wextra -I../lib/ |
