diff options
Diffstat (limited to 'tools/perf')
43 files changed, 473 insertions, 194 deletions
diff --git a/tools/perf/Documentation/perf.txt b/tools/perf/Documentation/perf.txt index 9c330cdfa973..71ebdf8125de 100644 --- a/tools/perf/Documentation/perf.txt +++ b/tools/perf/Documentation/perf.txt @@ -83,7 +83,7 @@ linkperf:perf-buildid-list[1], linkperf:perf-c2c[1], linkperf:perf-config[1], linkperf:perf-data[1], linkperf:perf-diff[1], linkperf:perf-evlist[1], linkperf:perf-ftrace[1], linkperf:perf-help[1], linkperf:perf-inject[1], -linkperf:perf-intel-pt[1], linkperf:perf-kallsyms[1], +linkperf:perf-intel-pt[1], linkperf:perf-iostat[1], linkperf:perf-kallsyms[1], linkperf:perf-kmem[1], linkperf:perf-kvm[1], linkperf:perf-lock[1], linkperf:perf-mem[1], linkperf:perf-probe[1], linkperf:perf-sched[1], linkperf:perf-script[1], linkperf:perf-test[1], diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 96ad944ca6a8..f3bf9297bcc0 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -272,6 +272,9 @@ ifdef PYTHON_CONFIG PYTHON_EMBED_LIBADD := $(call grep-libs,$(PYTHON_EMBED_LDOPTS)) -lutil PYTHON_EMBED_CCOPTS := $(shell $(PYTHON_CONFIG_SQ) --includes 2>/dev/null) FLAGS_PYTHON_EMBED := $(PYTHON_EMBED_CCOPTS) $(PYTHON_EMBED_LDOPTS) + ifeq ($(CC_NO_CLANG), 0) + PYTHON_EMBED_CCOPTS := $(filter-out -ffat-lto-objects, $(PYTHON_EMBED_CCOPTS)) + endif endif FEATURE_CHECK_CFLAGS-libpython := $(PYTHON_EMBED_CCOPTS) @@ -790,6 +793,9 @@ else LDFLAGS += $(PERL_EMBED_LDFLAGS) EXTLIBS += $(PERL_EMBED_LIBADD) CFLAGS += -DHAVE_LIBPERL_SUPPORT + ifeq ($(CC_NO_CLANG), 0) + CFLAGS += -Wno-compound-token-split-by-macro + endif $(call detected,CONFIG_LIBPERL) endif endif diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c index 86e2e926aa0e..e8b577d33e53 100644 --- a/tools/perf/arch/arm64/util/arm-spe.c +++ b/tools/perf/arch/arm64/util/arm-spe.c @@ -148,6 +148,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, bool privileged = perf_event_paranoid_check(-1); struct evsel *tracking_evsel; int err; + u64 bit; sper->evlist = evlist; @@ -239,6 +240,21 @@ static int arm_spe_recording_options(struct auxtrace_record *itr, arm_spe_set_timestamp(itr, arm_spe_evsel); } + /* + * Set this only so that perf report knows that SPE generates memory info. It has no effect + * on the opening of the event or the SPE data produced. + */ + evsel__set_sample_bit(arm_spe_evsel, DATA_SRC); + + /* + * The PHYS_ADDR flag does not affect the driver behaviour, it is used to + * inform that the resulting output's SPE samples contain physical addresses + * where applicable. + */ + bit = perf_pmu__format_bits(&arm_spe_pmu->format, "pa_enable"); + if (arm_spe_evsel->core.attr.config & bit) + evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR); + /* Add dummy event to keep tracking */ err = parse_events(evlist, "dummy:u", NULL); if (err) diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c index d2ce31e28cd7..41c1596e5207 100644 --- a/tools/perf/arch/arm64/util/machine.c +++ b/tools/perf/arch/arm64/util/machine.c @@ -8,27 +8,6 @@ #include "callchain.h" #include "record.h" -/* On arm64, kernel text segment starts at high memory address, - * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory - * address, like 0xffff 0000 00ax xxxx. When only small amount of - * memory is used by modules, gap between end of module's text segment - * and start of kernel text segment may reach 2G. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -#define SYMBOL_LIMIT (1 << 12) /* 4K */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if ((strchr(p->name, '[') && strchr(c->name, '[') == NULL) || - (strchr(p->name, '[') == NULL && strchr(c->name, '['))) - /* Limit range of last symbol in module and kernel */ - p->end += SYMBOL_LIMIT; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} - void arch__add_leaf_frame_record_opts(struct record_opts *opts) { opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask; diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build index 8a79c4126e5b..0115f3166568 100644 --- a/tools/perf/arch/powerpc/util/Build +++ b/tools/perf/arch/powerpc/util/Build @@ -1,5 +1,4 @@ perf-y += header.o -perf-y += machine.o perf-y += kvm-stat.o perf-y += perf_regs.o perf-y += mem-events.o diff --git a/tools/perf/arch/powerpc/util/machine.c b/tools/perf/arch/powerpc/util/machine.c deleted file mode 100644 index e652a1aa8132..000000000000 --- a/tools/perf/arch/powerpc/util/machine.c +++ /dev/null @@ -1,25 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 - -#include <inttypes.h> -#include <stdio.h> -#include <string.h> -#include <internal/lib.h> // page_size -#include "debug.h" -#include "symbol.h" - -/* On powerpc kernel text segment start at memory addresses, 0xc000000000000000 - * whereas the modules are located at very high memory addresses, - * for example 0xc00800000xxxxxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very high. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ - -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Limit the range of last kernel symbol */ - p->end += page_size; - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/arch/s390/util/machine.c b/tools/perf/arch/s390/util/machine.c index 7644a4f6d4a4..98bc3f39d5f3 100644 --- a/tools/perf/arch/s390/util/machine.c +++ b/tools/perf/arch/s390/util/machine.c @@ -35,19 +35,3 @@ int arch__fix_module_text_start(u64 *start, u64 *size, const char *name) return 0; } - -/* On s390 kernel text segment start is located at very low memory addresses, - * for example 0x10000. Modules are located at very high memory addresses, - * for example 0x3ff xxxx xxxx. The gap between end of kernel text segment - * and beginning of first module's text segment is very big. - * Therefore do not fill this gap and do not assign it to the kernel dso map. - */ -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - if (strchr(p->name, '[') == NULL && strchr(c->name, '[')) - /* Last kernel symbol mapped to end of page */ - p->end = roundup(p->end, page_size); - else - p->end = c->start; - pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end); -} diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c index 134612bde0cb..4256dc5d6236 100644 --- a/tools/perf/bench/epoll-ctl.c +++ b/tools/perf/bench/epoll-ctl.c @@ -222,13 +222,20 @@ static void init_fdmaps(struct worker *w, int pct) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0; + int nrcpus; + size_t size; if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -252,22 +259,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) init_fdmaps(w, 50); if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c index 37de970c9743..2728b0140853 100644 --- a/tools/perf/bench/epoll-wait.c +++ b/tools/perf/bench/epoll-wait.c @@ -291,9 +291,11 @@ static void print_summary(void) static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) { pthread_attr_t thread_attr, *attrp = NULL; - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i, j; int ret = 0, events = EPOLLIN; + int nrcpus; + size_t size; if (oneshot) events |= EPOLLONESHOT; @@ -306,6 +308,11 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) if (!noaffinity) pthread_attr_init(&thread_attr); + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < nthreads; i++) { struct worker *w = &worker[i]; @@ -341,22 +348,28 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu) } if (!noaffinity) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, + size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } attrp = &thread_attr; } ret = pthread_create(&w->thread, attrp, workerfn, (void *)(struct worker *) w); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); if (!noaffinity) pthread_attr_destroy(&thread_attr); diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c index dbcecec4eeda..f05db4cf983d 100644 --- a/tools/perf/bench/futex-hash.c +++ b/tools/perf/bench/futex-hash.c @@ -122,12 +122,14 @@ static void print_summary(void) int bench_futex_hash(int argc, const char **argv) { int ret = 0; - cpu_set_t cpuset; + cpu_set_t *cpuset; struct sigaction act; unsigned int i; pthread_attr_t thread_attr; struct worker *worker = NULL; struct perf_cpu_map *cpu; + int nrcpus; + size_t size; argc = parse_options(argc, argv, options, bench_futex_hash_usage, 0); if (argc) { @@ -170,25 +172,35 @@ int bench_futex_hash(int argc, const char **argv) threads_starting = params.nthreads; pthread_attr_init(&thread_attr); gettimeofday(&bench__start, NULL); + + nrcpus = perf_cpu_map__nr(cpu); + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; worker[i].futex = calloc(params.nfutexes, sizeof(*worker[i].futex)); if (!worker[i].futex) goto errmem; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); - ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset); - if (ret) + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); + ret = pthread_attr_setaffinity_np(&thread_attr, size, cpuset); + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); - + } ret = pthread_create(&worker[i].thread, &thread_attr, workerfn, (void *)(struct worker *) &worker[i]); - if (ret) + if (ret) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); pthread_attr_destroy(&thread_attr); pthread_mutex_lock(&thread_lock); diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c index 6fc9a3d55c1f..0abb3f7ee24f 100644 --- a/tools/perf/bench/futex-lock-pi.c +++ b/tools/perf/bench/futex-lock-pi.c @@ -120,11 +120,17 @@ static void *workerfn(void *arg) static void create_threads(struct worker *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + for (i = 0; i < params.nthreads; i++) { worker[i].tid = i; @@ -135,15 +141,20 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr, } else worker[i].futex = &global_futex; - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) + if (pthread_create(&w[i].thread, &thread_attr, workerfn, &worker[i])) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } int bench_futex_lock_pi(int argc, const char **argv) diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c index 2f59d5d1c509..b6faabfafb8e 100644 --- a/tools/perf/bench/futex-requeue.c +++ b/tools/perf/bench/futex-requeue.c @@ -123,22 +123,33 @@ static void *workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c index 861deb934745..e47f46a3a47e 100644 --- a/tools/perf/bench/futex-wake-parallel.c +++ b/tools/perf/bench/futex-wake-parallel.c @@ -144,22 +144,33 @@ static void *blocked_workerfn(void *arg __maybe_unused) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; + int nrcpus = perf_cpu_map__nr(cpu); + size_t size; threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, blocked_workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void print_run(struct thread_data *waking_worker, unsigned int run_num) diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c index cfda48bef1d7..201a3555f09a 100644 --- a/tools/perf/bench/futex-wake.c +++ b/tools/perf/bench/futex-wake.c @@ -97,22 +97,32 @@ static void print_summary(void) static void block_threads(pthread_t *w, pthread_attr_t thread_attr, struct perf_cpu_map *cpu) { - cpu_set_t cpuset; + cpu_set_t *cpuset; unsigned int i; - + size_t size; + int nrcpus = perf_cpu_map__nr(cpu); threads_starting = params.nthreads; + cpuset = CPU_ALLOC(nrcpus); + BUG_ON(!cpuset); + size = CPU_ALLOC_SIZE(nrcpus); + /* create and block all threads */ for (i = 0; i < params.nthreads; i++) { - CPU_ZERO(&cpuset); - CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset); + CPU_ZERO_S(size, cpuset); + CPU_SET_S(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, size, cpuset); - if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset)) + if (pthread_attr_setaffinity_np(&thread_attr, size, cpuset)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_attr_setaffinity_np"); + } - if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) + if (pthread_create(&w[i], &thread_attr, workerfn, NULL)) { + CPU_FREE(cpuset); err(EXIT_FAILURE, "pthread_create"); + } } + CPU_FREE(cpuset); } static void toggle_done(int sig __maybe_unused, diff --git a/tools/perf/bench/numa.c b/tools/perf/bench/numa.c index f2640179ada9..d5289fa58a4f 100644 --- a/tools/perf/bench/numa.c +++ b/tools/perf/bench/numa.c @@ -34,6 +34,7 @@ #include <linux/numa.h> #include <linux/zalloc.h> +#include "../util/header.h" #include <numa.h> #include <numaif.h> @@ -54,7 +55,7 @@ struct thread_data { int curr_cpu; - cpu_set_t bind_cpumask; + cpu_set_t *bind_cpumask; int bind_node; u8 *process_data; int process_nr; @@ -266,71 +267,117 @@ static bool node_has_cpus(int node) return ret; } -static cpu_set_t bind_to_cpu(int target_cpu) +static cpu_set_t *bind_to_cpu(int target_cpu) { - cpu_set_t orig_mask, mask; - int ret; + int nrcpus = numa_num_possible_cpus(); + cpu_set_t *orig_mask, *mask; + size_t size; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); + + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; - CPU_ZERO(&mask); + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; + + CPU_ZERO_S(size, mask); if (target_cpu == -1) { int cpu; for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { - BUG_ON(target_cpu < 0 || target_cpu >= g->p.nr_cpus); - CPU_SET(target_cpu, &mask); + if (target_cpu < 0 || target_cpu >= g->p.nr_cpus) + goto err; + + CPU_SET_S(target_cpu, size, mask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); + return NULL; } -static cpu_set_t bind_to_node(int target_node) +static cpu_set_t *bind_to_node(int target_node) { - cpu_set_t orig_mask, mask; + int nrcpus = numa_num_possible_cpus(); + size_t size; + cpu_set_t *orig_mask, *mask; int cpu; - int ret; - ret = sched_getaffinity(0, sizeof(orig_mask), &orig_mask); - BUG_ON(ret); + orig_mask = CPU_ALLOC(nrcpus); + BUG_ON(!orig_mask); + size = CPU_ALLOC_SIZE(nrcpus); + CPU_ZERO_S(size, orig_mask); - CPU_ZERO(&mask); + if (sched_getaffinity(0, size, orig_mask)) + goto err_out; + + mask = CPU_ALLOC(nrcpus); + if (!mask) + goto err_out; + + CPU_ZERO_S(size, mask); if (target_node == NUMA_NO_NODE) { for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } else { struct bitmask *cpumask = numa_allocate_cpumask(); - BUG_ON(!cpumask); + if (!cpumask) + goto err; + if (!numa_node_to_cpus(target_node, cpumask)) { for (cpu = 0; cpu < (int)cpumask->size; cpu++) { if (numa_bitmask_isbitset(cpumask, cpu)) - CPU_SET(cpu, &mask); + CPU_SET_S(cpu, size, mask); } } numa_free_cpumask(cpumask); } - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + if (sched_setaffinity(0, size, mask)) + goto err; return orig_mask; + +err: + CPU_FREE(mask); +err_out: + CPU_FREE(orig_mask); + + /* BUG_ON due to failure in allocation of orig_mask/mask */ + BUG_ON(-1); + return NULL; } -static void bind_to_cpumask(cpu_set_t mask) +static void bind_to_cpumask(cpu_set_t *mask) { int ret; + size_t size = CPU_ALLOC_SIZE(numa_num_possible_cpus()); - ret = sched_setaffinity(0, sizeof(mask), &mask); - BUG_ON(ret); + ret = sched_setaffinity(0, size, mask); + if (ret) { + CPU_FREE(mask); + BUG_ON(ret); + } } static void mempol_restore(void) @@ -376,7 +423,7 @@ do { \ static u8 *alloc_data(ssize_t bytes0, int map_flags, int init_zero, int init_cpu0, int thp, int init_random) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask = NULL; ssize_t bytes; u8 *buf; int ret; @@ -434,6 +481,7 @@ static u8 *alloc_data(ssize_t bytes0, int map_flags, /* Restore affinity: */ if (init_cpu0) { bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); mempol_restore(); } @@ -585,10 +633,16 @@ static int parse_setup_cpu_list(void) return -1; } + if (is_cpu_online(bind_cpu_0) != 1 || is_cpu_online(bind_cpu_1) != 1) { + printf("\nTest not applicable, bind_cpu_0 or bind_cpu_1 is offline\n"); + return -1; + } + BUG_ON(bind_cpu_0 < 0 || bind_cpu_1 < 0); BUG_ON(bind_cpu_0 > bind_cpu_1); for (bind_cpu = bind_cpu_0; bind_cpu <= bind_cpu_1; bind_cpu += step) { + size_t size = CPU_ALLOC_SIZE(g->p.nr_cpus); int i; for (i = 0; i < mul; i++) { @@ -608,10 +662,15 @@ static int parse_setup_cpu_list(void) tprintf("%2d", bind_cpu); } - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(size, td->bind_cpumask); for (cpu = bind_cpu; cpu < bind_cpu+bind_len; cpu++) { - BUG_ON(cpu < 0 || cpu >= g->p.nr_cpus); - CPU_SET(cpu, &td->bind_cpumask); + if (cpu < 0 || cpu >= g->p.nr_cpus) { + CPU_FREE(td->bind_cpumask); + BUG_ON(-1); + } + CPU_SET_S(cpu, size, td->bind_cpumask); } t++; } @@ -752,8 +811,6 @@ static int parse_nodes_opt(const struct option *opt __maybe_unused, return parse_node_list(arg); } -#define BIT(x) (1ul << x) - static inline uint32_t lfsr_32(uint32_t lfsr) { const uint32_t taps = BIT(1) | BIT(5) | BIT(6) | BIT(31); @@ -1241,7 +1298,7 @@ static void *worker_thread(void *__tdata) * by migrating to CPU#0: */ if (first_task && g->p.perturb_secs && (int)(stop.tv_sec - last_perturbance) >= g->p.perturb_secs) { - cpu_set_t orig_mask; + cpu_set_t *orig_mask; int target_cpu; int this_cpu; @@ -1265,6 +1322,7 @@ static void *worker_thread(void *__tdata) printf(" (injecting perturbalance, moved to CPU#%d)\n", target_cpu); bind_to_cpumask(orig_mask); + CPU_FREE(orig_mask); } if (details >= 3) { @@ -1398,21 +1456,31 @@ static void init_thread_data(void) for (t = 0; t < g->p.nr_tasks; t++) { struct thread_data *td = g->threads + t; + size_t cpuset_size = CPU_ALLOC_SIZE(g->p.nr_cpus); int cpu; /* Allow all nodes by default: */ td->bind_node = NUMA_NO_NODE; /* Allow all CPUs by default: */ - CPU_ZERO(&td->bind_cpumask); + td->bind_cpumask = CPU_ALLOC(g->p.nr_cpus); + BUG_ON(!td->bind_cpumask); + CPU_ZERO_S(cpuset_size, td->bind_cpumask); for (cpu = 0; cpu < g->p.nr_cpus; cpu++) - CPU_SET(cpu, &td->bind_cpumask); + CPU_SET_S(cpu, cpuset_size, td->bind_cpumask); } } static void deinit_thread_data(void) { ssize_t size = sizeof(*g->threads)*g->p.nr_tasks; + int t; + + /* Free the bind_cpumask allocated for thread_data */ + for (t = 0; t < g->p.nr_tasks; t++) { + struct thread_data *td = g->threads + t; + CPU_FREE(td->bind_cpumask); + } free_data(g->threads, size); } diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index ba74fab02e62..069825c48d40 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -989,8 +989,11 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru struct mmap *overwrite_mmap = evlist->overwrite_mmap; struct perf_cpu_map *cpus = evlist->core.user_requested_cpus; - thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, - thread_data->mask->maps.nbits); + if (cpu_map__is_dummy(cpus)) + thread_data->nr_mmaps = nr_mmaps; + else + thread_data->nr_mmaps = bitmap_weight(thread_data->mask->maps.bits, + thread_data->mask->maps.nbits); if (mmap) { thread_data->maps = zalloc(thread_data->nr_mmaps * sizeof(struct mmap *)); if (!thread_data->maps) @@ -1007,16 +1010,17 @@ static int record__thread_data_init_maps(struct record_thread *thread_data, stru thread_data->nr_mmaps, thread_data->maps, thread_data->overwrite_maps); for (m = 0, tm = 0; m < nr_mmaps && tm < thread_data->nr_mmaps; m++) { - if (test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { + if (cpu_map__is_dummy(cpus) || + test_bit(cpus->map[m].cpu, thread_data->mask->maps.bits)) { if (thread_data->maps) { thread_data->maps[tm] = &mmap[m]; pr_debug2("thread_data[%p]: cpu%d: maps[%d] -> mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } if (thread_data->overwrite_maps) { thread_data->overwrite_maps[tm] = &overwrite_mmap[m]; pr_debug2("thread_data[%p]: cpu%d: ow_maps[%d] -> ow_mmap[%d]\n", - thread_data, cpus->map[m].cpu, tm, m); + thread_data, perf_cpu_map__cpu(cpus, m).cpu, tm, m); } tm++; } @@ -3329,6 +3333,9 @@ static void record__mmap_cpu_mask_init(struct mmap_cpu_mask *mask, struct perf_c { int c; + if (cpu_map__is_dummy(cpus)) + return; + for (c = 0; c < cpus->nr; c++) set_bit(cpus->map[c].cpu, mask->bits); } @@ -3680,6 +3687,11 @@ static int record__init_thread_masks(struct record *rec) if (!record__threads_enabled(rec)) return record__init_thread_default_masks(rec, cpus); + if (cpu_map__is_dummy(cpus)) { + pr_err("--per-thread option is mutually exclusive to parallel streaming mode.\n"); + return -EINVAL; + } + switch (rec->opts.threads_spec) { case THREAD_SPEC__CPU: ret = record__init_thread_cpu_masks(rec, cpus); diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 1ad75c7ba074..afe4a5539ecc 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -353,6 +353,7 @@ static int report__setup_sample_type(struct report *rep) struct perf_session *session = rep->session; u64 sample_type = evlist__combined_sample_type(session->evlist); bool is_pipe = perf_data__is_pipe(session->data); + struct evsel *evsel; if (session->itrace_synth_opts->callchain || session->itrace_synth_opts->add_callchain || @@ -407,6 +408,19 @@ static int report__setup_sample_type(struct report *rep) } if (sort__mode == SORT_MODE__MEMORY) { + /* + * FIXUP: prior to kernel 5.18, Arm SPE missed to set + * PERF_SAMPLE_DATA_SRC bit in sample type. For backward + * compatibility, set the bit if it's an old perf data file. + */ + evlist__for_each_entry(session->evlist, evsel) { + if (strstr(evsel->name, "arm_spe") && + !(sample_type & PERF_SAMPLE_DATA_SRC)) { + evsel->core.attr.sample_type |= PERF_SAMPLE_DATA_SRC; + sample_type |= PERF_SAMPLE_DATA_SRC; + } + } + if (!is_pipe && !(sample_type & PERF_SAMPLE_DATA_SRC)) { ui__error("Selected --mem-mode but no mem data. " "Did you call perf record without -d?\n"); diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index a2f117936188..cf5eab5431b4 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -461,7 +461,7 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session) return -EINVAL; if (PRINT_FIELD(DATA_SRC) && - evsel__check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC)) + evsel__do_check_stype(evsel, PERF_SAMPLE_DATA_SRC, "DATA_SRC", PERF_OUTPUT_DATA_SRC, allow_user_set)) return -EINVAL; if (PRINT_FIELD(WEIGHT) && diff --git a/tools/perf/perf.c b/tools/perf/perf.c index 2f6b67189b42..0170cb0819d6 100644 --- a/tools/perf/perf.c +++ b/tools/perf/perf.c @@ -55,6 +55,7 @@ struct cmd_struct { }; static struct cmd_struct commands[] = { + { "archive", NULL, 0 }, { "buildid-cache", cmd_buildid_cache, 0 }, { "buildid-list", cmd_buildid_list, 0 }, { "config", cmd_config, 0 }, @@ -62,6 +63,7 @@ static struct cmd_struct commands[] = { { "diff", cmd_diff, 0 }, { "evlist", cmd_evlist, 0 }, { "help", cmd_help, 0 }, + { "iostat", NULL, 0 }, { "kallsyms", cmd_kallsyms, 0 }, { "list", cmd_list, 0 }, { "record", cmd_record, 0 }, @@ -360,6 +362,8 @@ static void handle_internal_command(int argc, const char **argv) for (i = 0; i < ARRAY_SIZE(commands); i++) { struct cmd_struct *p = commands+i; + if (p->fn == NULL) + continue; if (strcmp(p->cmd, cmd)) continue; exit(run_builtin(p, argc, argv)); @@ -434,7 +438,7 @@ void pthread__unblock_sigwinch(void) static int libperf_print(enum libperf_print_level level, const char *fmt, va_list ap) { - return eprintf(level, verbose, fmt, ap); + return veprintf(level, verbose, fmt, ap); } int main(int argc, const char **argv) diff --git a/tools/perf/tests/attr/README b/tools/perf/tests/attr/README index 454505d343fa..eb3f7d4bb324 100644 --- a/tools/perf/tests/attr/README +++ b/tools/perf/tests/attr/README @@ -60,6 +60,7 @@ Following tests are defined (with perf commands): perf record -R kill (test-record-raw) perf record -c 2 -e arm_spe_0// -- kill (test-record-spe-period) perf record -e arm_spe_0/period=3/ -- kill (test-record-spe-period-term) + perf record -e arm_spe_0/pa_enable=1/ -- kill (test-record-spe-physical-address) perf stat -e cycles kill (test-stat-basic) perf stat kill (test-stat-default) perf stat -d kill (test-stat-detailed-1) diff --git a/tools/perf/tests/attr/test-record-spe-physical-address b/tools/perf/tests/attr/test-record-spe-physical-address new file mode 100644 index 000000000000..7ebcf5012ce3 --- /dev/null +++ b/tools/perf/tests/attr/test-record-spe-physical-address @@ -0,0 +1,12 @@ +[config] +command = record +args = --no-bpf-event -e arm_spe_0/pa_enable=1/ -- kill >/dev/null 2>&1 +ret = 1 +arch = aarch64 + +[event-10:base-record-spe] +# 622727 is the decimal of IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC|PHYS_ADDR +sample_type=622727 + +# dummy event +[event-1:base-record-spe]
\ No newline at end of file diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c index 2dab2d262060..afdca7f2959f 100644 --- a/tools/perf/tests/dwarf-unwind.c +++ b/tools/perf/tests/dwarf-unwind.c @@ -122,7 +122,7 @@ NO_TAIL_CALL_ATTRIBUTE noinline int test_dwarf_unwind__thread(struct thread *thr } err = unwind__get_entries(unwind_entry, &cnt, thread, - &sample, MAX_STACK); + &sample, MAX_STACK, false); if (err) pr_debug("unwind failed\n"); else if (cnt != MAX_STACK) { diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c index d12d0ad81801..4ad0dfbc8b21 100644 --- a/tools/perf/tests/perf-time-to-tsc.c +++ b/tools/perf/tests/perf-time-to-tsc.c @@ -47,6 +47,17 @@ } \ } +static int test__tsc_is_supported(struct test_suite *test __maybe_unused, + int subtest __maybe_unused) +{ + if (!TSC_IS_SUPPORTED) { + pr_debug("Test not supported on this architecture\n"); + return TEST_SKIP; + } + + return TEST_OK; +} + /** * test__perf_time_to_tsc - test converting perf time to TSC. * @@ -70,7 +81,7 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su struct perf_cpu_map *cpus = NULL; struct evlist *evlist = NULL; struct evsel *evsel = NULL; - int err = -1, ret, i; + int err = TEST_FAIL, ret, i; const char *comm1, *comm2; struct perf_tsc_conversion tc; struct perf_event_mmap_page *pc; @@ -79,10 +90,6 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su u64 test_time, comm1_time = 0, comm2_time = 0; struct mmap *md; - if (!TSC_IS_SUPPORTED) { - pr_debug("Test not supported on this architecture"); - return TEST_SKIP; - } threads = thread_map__new(-1, getpid(), UINT_MAX); CHECK_NOT_NULL__(threads); @@ -116,6 +123,10 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su evsel->core.attr.enable_on_exec = 0; } + if (evlist__open(evlist) == -ENOENT) { + err = TEST_SKIP; + goto out_err; + } CHECK__(evlist__open(evlist)); CHECK__(evlist__mmap(evlist, UINT_MAX)); @@ -124,8 +135,8 @@ static int test__perf_time_to_tsc(struct test_suite *test __maybe_unused, int su ret = perf_read_tsc_conversion(pc, &tc); if (ret) { if (ret == -EOPNOTSUPP) { - fprintf(stderr, " (not supported)"); - return 0; + pr_debug("perf_read_tsc_conversion is not supported in current kernel\n"); + err = TEST_SKIP; } goto out_err; } @@ -191,7 +202,7 @@ next_event: test_tsc >= comm2_tsc) goto out_err; - err = 0; + err = TEST_OK; out_err: evlist__delete(evlist); @@ -200,4 +211,15 @@ out_err: return err; } -DEFINE_SUITE("Convert perf time to TSC", perf_time_to_tsc); +static struct test_case time_to_tsc_tests[] = { + TEST_CASE_REASON("TSC support", tsc_is_supported, + "This architecture does not support"), + TEST_CASE_REASON("Perf time to TSC", perf_time_to_tsc, + "perf_read_tsc_conversion is not supported"), + { .name = NULL, } +}; + +struct test_suite suite__perf_time_to_tsc = { + .desc = "Convert perf time to TSC", + .test_cases = time_to_tsc_tests, +}; diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh index 6de53b7ef5ff..e4cb4f1806ff 100755 --- a/tools/perf/tests/shell/test_arm_coresight.sh +++ b/tools/perf/tests/shell/test_arm_coresight.sh @@ -29,7 +29,6 @@ cleanup_files() rm -f ${file} rm -f "${perfdata}.old" trap - exit term int - kill -2 $$ exit $glb_err } diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c index e4c641b240df..82cc396ef516 100644 --- a/tools/perf/util/annotate.c +++ b/tools/perf/util/annotate.c @@ -2047,6 +2047,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args) objdump_process.argv = objdump_argv; objdump_process.out = -1; objdump_process.err = -1; + objdump_process.no_stderr = 1; if (start_command(&objdump_process)) { pr_err("Failure starting to run %s\n", command); err = -1; diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index d2b64e3f588b..1a80151baed9 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -1033,10 +1033,11 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session) memset(&attr, 0, sizeof(struct perf_event_attr)); attr.size = sizeof(struct perf_event_attr); attr.type = PERF_TYPE_HARDWARE; - attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK; + attr.sample_type = evsel->core.attr.sample_type & + (PERF_SAMPLE_MASK | PERF_SAMPLE_PHYS_ADDR); attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID | PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC | - PERF_SAMPLE_WEIGHT; + PERF_SAMPLE_WEIGHT | PERF_SAMPLE_ADDR; if (spe->timeless_decoding) attr.sample_type &= ~(u64)PERF_SAMPLE_TIME; else diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c index 2242a885fbd7..4940be4a0569 100644 --- a/tools/perf/util/arm64-frame-pointer-unwind-support.c +++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c @@ -53,7 +53,7 @@ u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thr sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0; } - ret = unwind__get_entries(add_entry, &entries, thread, sample, 2); + ret = unwind__get_entries(add_entry, &entries, thread, sample, 2, true); sample->user_regs = old_regs; if (ret || entries.length != 2) diff --git a/tools/perf/util/c++/clang.cpp b/tools/perf/util/c++/clang.cpp index df7b18fb6b6e..1aad7d6d34aa 100644 --- a/tools/perf/util/c++/clang.cpp +++ b/tools/perf/util/c++/clang.cpp @@ -20,7 +20,11 @@ #include "llvm/Option/Option.h" #include "llvm/Support/FileSystem.h" #include "llvm/Support/ManagedStatic.h" +#if CLANG_VERSION_MAJOR >= 14 +#include "llvm/MC/TargetRegistry.h" +#else #include "llvm/Support/TargetRegistry.h" +#endif #include "llvm/Support/TargetSelect.h" #include "llvm/Target/TargetMachine.h" #include "llvm/Target/TargetOptions.h" diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c index d546ff724dbe..a27132e5a5ef 100644 --- a/tools/perf/util/header.c +++ b/tools/perf/util/header.c @@ -983,6 +983,57 @@ static int write_dir_format(struct feat_fd *ff, return do_write(ff, &data->dir.version, sizeof(data->dir.version)); } +/* + * Check whether a CPU is online + * + * Returns: + * 1 -> if CPU is online + * 0 -> if CPU is offline + * -1 -> error case + */ +int is_cpu_online(unsigned int cpu) +{ + char *str; + size_t strlen; + char buf[256]; + int status = -1; + struct stat statbuf; + + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d", cpu); + if (stat(buf, &statbuf) != 0) + return 0; + + /* + * Check if /sys/devices/system/cpu/cpux/online file + * exists. Some cases cpu0 won't have online file since + * it is not expected to be turned off generally. + * In kernels without CONFIG_HOTPLUG_CPU, this + * file won't exist + */ + snprintf(buf, sizeof(buf), + "/sys/devices/system/cpu/cpu%d/online", cpu); + if (stat(buf, &statbuf) != 0) + return 1; + + /* + * Read online file using sysfs__read_str. + * If read or open fails, return -1. + * If read succeeds, return value from file + * which gets stored in "str" + */ + snprintf(buf, sizeof(buf), + "devices/system/cpu/cpu%d/online", cpu); + + if (sysfs__read_str(buf, &str, &strlen) < 0) + return status; + + status = atoi(str); + + free(str); + return status; +} + #ifdef HAVE_LIBBPF_SUPPORT static int write_bpf_prog_info(struct feat_fd *ff, struct evlist *evlist __maybe_unused) diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index c9e3265832d9..0eb4bc29a5a4 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -158,6 +158,7 @@ int do_write(struct feat_fd *fd, const void *buf, size_t size); int write_padded(struct feat_fd *fd, const void *bf, size_t count, size_t count_aligned); +int is_cpu_online(unsigned int cpu); /* * arch specific callback */ diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c index b80048546451..95391236f5f6 100644 --- a/tools/perf/util/machine.c +++ b/tools/perf/util/machine.c @@ -2987,7 +2987,7 @@ static int thread__resolve_callchain_unwind(struct thread *thread, return 0; return unwind__get_entries(unwind_entry, cursor, - thread, sample, max_stack); + thread, sample, max_stack, false); } int thread__resolve_callchain(struct thread *thread, diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 24997925ae00..dd84fed698a3 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1523,7 +1523,9 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, bool use_uncore_alias; LIST_HEAD(config_terms); - if (verbose > 1) { + pmu = parse_state->fake_pmu ?: perf_pmu__find(name); + + if (verbose > 1 && !(pmu && pmu->selectable)) { fprintf(stderr, "Attempting to add event pmu '%s' with '", name); if (head_config) { @@ -1536,7 +1538,6 @@ int parse_events_add_pmu(struct parse_events_state *parse_state, fprintf(stderr, "' that may result in non-fatal errors\n"); } - pmu = parse_state->fake_pmu ?: perf_pmu__find(name); if (!pmu) { char *err_str; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 3b8dfe603e50..f9a320694b85 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -2095,6 +2095,7 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, bool needs_swap, union perf_event *error) { union perf_event *event; + u16 event_size; /* * Ensure we have enough space remaining to read @@ -2107,15 +2108,23 @@ prefetch_event(char *buf, u64 head, size_t mmap_size, if (needs_swap) perf_event_header__bswap(&event->header); - if (head + event->header.size <= mmap_size) + event_size = event->header.size; + if (head + event_size <= mmap_size) return event; /* We're not fetching the event so swap back again */ if (needs_swap) perf_event_header__bswap(&event->header); - pr_debug("%s: head=%#" PRIx64 " event->header_size=%#x, mmap_size=%#zx:" - " fuzzed or compressed perf.data?\n",__func__, head, event->header.size, mmap_size); + /* Check if the event fits into the next mmapped buf. */ + if (event_size <= mmap_size - head % page_size) { + /* Remap buf and fetch again. */ + return NULL; + } + + /* Invalid input. Event size should never exceed mmap_size. */ + pr_debug("%s: head=%#" PRIx64 " event->header.size=%#x, mmap_size=%#zx:" + " fuzzed or compressed perf.data?\n", __func__, head, event_size, mmap_size); return error; } @@ -2567,7 +2576,7 @@ int perf_session__process_events(struct perf_session *session) if (perf_data__is_pipe(session->data)) return __perf_session__process_pipe_events(session); - if (perf_data__is_dir(session->data)) + if (perf_data__is_dir(session->data) && session->data->dir.nr) return __perf_session__process_dir_events(session); return __perf_session__process_events(session); diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py index 483f05004e68..c255a2c90cd6 100644 --- a/tools/perf/util/setup.py +++ b/tools/perf/util/setup.py @@ -1,12 +1,14 @@ -from os import getenv +from os import getenv, path from subprocess import Popen, PIPE from re import sub cc = getenv("CC") cc_is_clang = b"clang version" in Popen([cc.split()[0], "-v"], stderr=PIPE).stderr.readline() +src_feature_tests = getenv('srctree') + '/tools/build/feature' def clang_has_option(option): - return [o for o in Popen([cc, option], stderr=PIPE).stderr.readlines() if b"unknown argument" in o] == [ ] + cc_output = Popen([cc, option, path.join(src_feature_tests, "test-hello.c") ], stderr=PIPE).stderr.readlines() + return [o for o in cc_output if ((b"unknown argument" in o) or (b"is not supported" in o))] == [ ] if cc_is_clang: from distutils.sysconfig import get_config_vars @@ -23,6 +25,8 @@ if cc_is_clang: vars[var] = sub("-fstack-protector-strong", "", vars[var]) if not clang_has_option("-fno-semantic-interposition"): vars[var] = sub("-fno-semantic-interposition", "", vars[var]) + if not clang_has_option("-ffat-lto-objects"): + vars[var] = sub("-ffat-lto-objects", "", vars[var]) from distutils.core import setup, Extension diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c index ee6f03481215..817a2de264b4 100644 --- a/tools/perf/util/stat.c +++ b/tools/perf/util/stat.c @@ -1,5 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include <errno.h> +#include <linux/err.h> #include <inttypes.h> #include <math.h> #include <string.h> @@ -311,7 +312,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals, if (!mask) { mask = hashmap__new(pkg_id_hash, pkg_id_equal, NULL); - if (!mask) + if (IS_ERR(mask)) return -ENOMEM; counter->per_pkg_mask = mask; diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c index 31cd59a2b66e..ecd377938eea 100644 --- a/tools/perf/util/symbol-elf.c +++ b/tools/perf/util/symbol-elf.c @@ -1290,7 +1290,7 @@ dso__load_sym_internal(struct dso *dso, struct map *map, struct symsrc *syms_ss, * For misannotated, zeroed, ASM function sizes. */ if (nr > 0) { - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); if (kmap) { /* diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index dea0fc495185..f72baf636724 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -101,11 +101,6 @@ static int prefix_underscores_count(const char *str) return tail - str; } -void __weak arch__symbols__fixup_end(struct symbol *p, struct symbol *c) -{ - p->end = c->start; -} - const char * __weak arch__normalize_symbol_name(const char *name) { return name; @@ -217,7 +212,8 @@ again: } } -void symbols__fixup_end(struct rb_root_cached *symbols) +/* Update zero-sized symbols using the address of the next symbol */ +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms) { struct rb_node *nd, *prevnd = rb_first_cached(symbols); struct symbol *curr, *prev; @@ -231,8 +227,29 @@ void symbols__fixup_end(struct rb_root_cached *symbols) prev = curr; curr = rb_entry(nd, struct symbol, rb_node); - if (prev->end == prev->start || prev->end != curr->start) - arch__symbols__fixup_end(prev, curr); + /* + * On some architecture kernel text segment start is located at + * some low memory address, while modules are located at high + * memory addresses (or vice versa). The gap between end of + * kernel text segment and beginning of first module's text + * segment is very big. Therefore do not fill this gap and do + * not assign it to the kernel dso map (kallsyms). + * + * In kallsyms, it determines module symbols using '[' character + * like in: + * ffffffffc1937000 T hdmi_driver_init [snd_hda_codec_hdmi] + */ + if (prev->end == prev->start) { + /* Last kernel/module symbol mapped to end of page */ + if (is_kallsyms && (!strchr(prev->name, '[') != + !strchr(curr->name, '['))) + prev->end = roundup(prev->end + 4096, 4096); + else + prev->end = curr->start; + + pr_debug4("%s sym:%s end:%#" PRIx64 "\n", + __func__, prev->name, prev->end); + } } /* Last entry */ @@ -1467,7 +1484,7 @@ int __dso__load_kallsyms(struct dso *dso, const char *filename, if (kallsyms__delta(kmap, filename, &delta)) return -1; - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, true); symbols__fixup_duplicate(&dso->symbols); if (dso->kernel == DSO_SPACE__KERNEL_GUEST) @@ -1659,7 +1676,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile) #undef bfd_asymbol_section #endif - symbols__fixup_end(&dso->symbols); + symbols__fixup_end(&dso->symbols, false); symbols__fixup_duplicate(&dso->symbols); dso->adjust_symbols = 1; diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h index fbf866d82dcc..0b893dcc8ea6 100644 --- a/tools/perf/util/symbol.h +++ b/tools/perf/util/symbol.h @@ -203,7 +203,7 @@ void __symbols__insert(struct rb_root_cached *symbols, struct symbol *sym, bool kernel); void symbols__insert(struct rb_root_cached *symbols, struct symbol *sym); void symbols__fixup_duplicate(struct rb_root_cached *symbols); -void symbols__fixup_end(struct rb_root_cached *symbols); +void symbols__fixup_end(struct rb_root_cached *symbols, bool is_kallsyms); void maps__fixup_end(struct maps *maps); typedef int (*mapfn_t)(u64 start, u64 len, u64 pgoff, void *data); @@ -241,7 +241,6 @@ const char *arch__normalize_symbol_name(const char *name); #define SYMBOL_A 0 #define SYMBOL_B 1 -void arch__symbols__fixup_end(struct symbol *p, struct symbol *c); int arch__compare_symbol_names(const char *namea, const char *nameb); int arch__compare_symbol_names_n(const char *namea, const char *nameb, unsigned int n); diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c index a74b517f7497..94aa40f6e348 100644 --- a/tools/perf/util/unwind-libdw.c +++ b/tools/perf/util/unwind-libdw.c @@ -200,7 +200,8 @@ frame_callback(Dwfl_Frame *state, void *arg) bool isactivation; if (!dwfl_frame_pc(state, &pc, NULL)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -208,7 +209,8 @@ frame_callback(Dwfl_Frame *state, void *arg) report_module(pc, ui); if (!dwfl_frame_pc(state, &pc, &isactivation)) { - pr_err("%s", dwfl_errmsg(-1)); + if (!ui->best_effort) + pr_err("%s", dwfl_errmsg(-1)); return DWARF_CB_ABORT; } @@ -222,7 +224,8 @@ frame_callback(Dwfl_Frame *state, void *arg) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, struct perf_sample *data, - int max_stack) + int max_stack, + bool best_effort) { struct unwind_info *ui, ui_buf = { .sample = data, @@ -231,6 +234,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, .cb = cb, .arg = arg, .max_stack = max_stack, + .best_effort = best_effort }; Dwarf_Word ip; int err = -EINVAL, i; diff --git a/tools/perf/util/unwind-libdw.h b/tools/perf/util/unwind-libdw.h index 0cbd2650e280..8c88bc4f2304 100644 --- a/tools/perf/util/unwind-libdw.h +++ b/tools/perf/util/unwind-libdw.h @@ -20,6 +20,7 @@ struct unwind_info { void *arg; int max_stack; int idx; + bool best_effort; struct unwind_entry entries[]; }; diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c index 71a353349181..41e29fc7648a 100644 --- a/tools/perf/util/unwind-libunwind-local.c +++ b/tools/perf/util/unwind-libunwind-local.c @@ -96,6 +96,7 @@ struct unwind_info { struct perf_sample *sample; struct machine *machine; struct thread *thread; + bool best_effort; }; #define dw_read(ptr, type, end) ({ \ @@ -553,7 +554,8 @@ static int access_reg(unw_addr_space_t __maybe_unused as, ret = perf_reg_value(&val, &ui->sample->user_regs, id); if (ret) { - pr_err("unwind: can't read reg %d\n", regnum); + if (!ui->best_effort) + pr_err("unwind: can't read reg %d\n", regnum); return ret; } @@ -666,7 +668,7 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, return -1; ret = unw_init_remote(&c, addr_space, ui); - if (ret) + if (ret && !ui->best_effort) display_error(ret); while (!ret && (unw_step(&c) > 0) && i < max_stack) { @@ -704,12 +706,14 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb, static int _unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { struct unwind_info ui = { .sample = data, .thread = thread, .machine = thread->maps->machine, + .best_effort = best_effort }; if (!data->user_regs.regs) diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c index e89a5479b361..509c287ee762 100644 --- a/tools/perf/util/unwind-libunwind.c +++ b/tools/perf/util/unwind-libunwind.c @@ -80,9 +80,11 @@ void unwind__finish_access(struct maps *maps) int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack) + struct perf_sample *data, int max_stack, + bool best_effort) { if (thread->maps->unwind_libunwind_ops) - return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, max_stack); + return thread->maps->unwind_libunwind_ops->get_entries(cb, arg, thread, data, + max_stack, best_effort); return 0; } diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h index ab8ad469c8de..b2a03fa5289b 100644 --- a/tools/perf/util/unwind.h +++ b/tools/perf/util/unwind.h @@ -23,13 +23,19 @@ struct unwind_libunwind_ops { void (*finish_access)(struct maps *maps); int (*get_entries)(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, bool best_effort); }; #ifdef HAVE_DWARF_UNWIND_SUPPORT +/* + * When best_effort is set, don't report errors and fail silently. This could + * be expanded in the future to be more permissive about things other than + * error messages. + */ int unwind__get_entries(unwind_entry_cb_t cb, void *arg, struct thread *thread, - struct perf_sample *data, int max_stack); + struct perf_sample *data, int max_stack, + bool best_effort); /* libunwind specific */ #ifdef HAVE_LIBUNWIND_SUPPORT #ifndef LIBUNWIND__ARCH_REG_ID @@ -65,7 +71,8 @@ unwind__get_entries(unwind_entry_cb_t cb __maybe_unused, void *arg __maybe_unused, struct thread *thread __maybe_unused, struct perf_sample *data __maybe_unused, - int max_stack __maybe_unused) + int max_stack __maybe_unused, + bool best_effort __maybe_unused) { return 0; } |