From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-16.8 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_CR_TRAILER,INCLUDES_PATCH, MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS,URIBL_BLOCKED,USER_AGENT_GIT autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 32E0DC4320E for ; Tue, 17 Aug 2021 08:23:52 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 1B72160F41 for ; Tue, 17 Aug 2021 08:23:52 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S239285AbhHQIYW (ORCPT ); Tue, 17 Aug 2021 04:24:22 -0400 Received: from mga07.intel.com ([134.134.136.100]:11537 "EHLO mga07.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S239191AbhHQIYO (ORCPT ); Tue, 17 Aug 2021 04:24:14 -0400 X-IronPort-AV: E=McAfee;i="6200,9189,10078"; a="279763181" X-IronPort-AV: E=Sophos;i="5.84,328,1620716400"; d="scan'208";a="279763181" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by orsmga105.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 17 Aug 2021 01:23:41 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.84,328,1620716400"; d="scan'208";a="471080197" Received: from nntpat99-84.inn.intel.com ([10.125.99.84]) by orsmga008.jf.intel.com with ESMTP; 17 Aug 2021 01:23:38 -0700 From: Alexey Bayduraev To: Arnaldo Carvalho de Melo Cc: Jiri Olsa , Namhyung Kim , Alexander Shishkin , Peter Zijlstra , Ingo Molnar , linux-kernel , Andi Kleen , Adrian Hunter , Alexander Antonov , Alexei Budankov , Riccardo Mancini Subject: [PATCH v11 03/24] perf record: Introduce thread specific data array Date: Tue, 17 Aug 2021 11:23:06 +0300 Message-Id: <4530ada74ed3c85c2dabae6e26365ab1a8403211.1629186429.git.alexey.v.bayduraev@linux.intel.com> X-Mailer: git-send-email 2.19.0 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Introduce thread specific data object and array of such objects to store and manage thread local data. Implement functions to allocate, initialize, finalize and release thread specific data. Thread local maps and overwrite_maps arrays keep pointers to mmap buffer objects to serve according to maps thread mask. Thread local pollfd array keeps event fds connected to mmaps buffers according to maps thread mask. Thread control commands are delivered via thread local comm pipes and ctlfd_pos fd. External control commands (--control option) are delivered via evlist ctlfd_pos fd and handled by the main tool thread. Acked-by: Namhyung Kim Reviewed-by: Riccardo Mancini Tested-by: Riccardo Mancini Signed-off-by: Alexey Bayduraev --- tools/perf/builtin-record.c | 254 +++++++++++++++++++++++++++++++++++- 1 file changed, 251 insertions(+), 3 deletions(-) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 021a607510b5..50bdf544eeeb 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -58,6 +58,7 @@ #include #include #include +#include #include #include #ifdef HAVE_EVENTFD_SUPPORT @@ -92,6 +93,23 @@ struct thread_mask { struct mmap_cpu_mask affinity; }; +struct record_thread { + pid_t tid; + struct thread_mask *mask; + struct { + int msg[2]; + int ack[2]; + } pipes; + struct fdarray pollfd; + int ctlfd_pos; + int nr_mmaps; + struct mmap **maps; + struct mmap **overwrite_maps; + struct record *rec; + unsigned long long samples; + unsigned long waking; +}; + struct record { struct perf_tool tool; struct record_opts opts; @@ -118,6 +136,7 @@ struct record { unsigned long output_max_size; /* = 0: unlimited */ int nr_threads; struct thread_mask *thread_masks; + struct record_thread *thread_data; }; static volatile int done; @@ -130,6 +149,13 @@ static const char *affinity_tags[PERF_AFFINITY_MAX] = { "SYS", "NODE", "CPU" }; +#ifndef HAVE_GETTID +static inline pid_t gettid(void) +{ + return (pid_t)syscall(__NR_gettid); +} +#endif + static bool switch_output_signal(struct record *rec) { return rec->switch_output.signal && @@ -847,9 +873,225 @@ static int record__kcore_copy(struct machine *machine, struct perf_data *data) return kcore_copy(from_dir, kcore_dir); } +static void record__thread_data_init_pipes(struct record_thread *thread_data) +{ + thread_data->pipes.msg[0] = -1; + thread_data->pipes.msg[1] = -1; + thread_data->pipes.ack[0] = -1; + thread_data->pipes.ack[1] = -1; +} + +static int record__thread_data_open_pipes(struct record_thread *thread_data) +{ + if (pipe(thread_data->pipes.msg)) { + pr_err("Failed to create thread msg communication pipe: %s\n", strerror(errno)); + return -ENOMEM; + } + + if (pipe(thread_data->pipes.ack)) { + pr_err("Failed to create thread ack communication pipe: %s\n", strerror(errno)); + close(thread_data->pipes.msg[0]); + thread_data->pipes.msg[0] = -1; + close(thread_data->pipes.msg[1]); + thread_data->pipes.msg[1] = -1; + return -ENOMEM; + } + + pr_debug2("thread_data[%p]: msg=[%d,%d], ack=[%d,%d]\n", thread_data, + thread_data->pipes.msg[0], thread_data->pipes.msg[1], + thread_data->pipes.ack[0], thread_data->pipes.ack[1]); + + return 0; +} + +static void record__thread_data_close_pipes(struct record_thread *thread_data) +{ + if (thread_data->pipes.msg[0] != -1) { + close(thread_data->pipes.msg[0]); + thread_data->pipes.msg[0] = -1; + } + if (thread_data->pipes.msg[1] != -1) { + close(thread_data->pipes.msg[1]); + thread_data->pipes.msg[1] = -1; + } + if (thread_data->pipes.ack[0] != -1) { + close(thread_data->pipes.ack[0]); + thread_data->pipes.ack[0] = -1; + } + if (thread_data->pipes.ack[1] != -1) { + close(thread_data->pipes.ack[1]); + thread_data->pipes.ack[1] = -1; + } +} + +static int record__thread_data_init_maps(struct record_thread *thread_data, struct evlist *evlist) +{ + int m, tm, nr_mmaps = evlist->core.nr_mmaps; + struct mmap *mmap = evlist->mmap; + struct mmap *overwrite_mmap = evlist->overwrite_mmap; + struct perf_cpu_map *cpus = evlist->core.cpus; + + 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) { + pr_err("Failed to allocate thread maps\n"); + return -ENOMEM; + } + } + if (overwrite_mmap) { + thread_data->overwrite_maps = zalloc(thread_data->nr_mmaps * sizeof(struct mmap *)); + if (!thread_data->overwrite_maps) { + pr_err("Failed to allocate thread overwrite maps\n"); + zfree(&thread_data->maps); + return -ENOMEM; + } + } + pr_debug2("thread_data[%p]: nr_mmaps=%d, maps=%p, ow_maps=%p\n", thread_data, + 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], thread_data->mask->maps.bits)) { + if (thread_data->maps) { + thread_data->maps[tm] = &mmap[m]; + pr_debug2("thread_data[%p]: maps[%d] -> mmap[%d], cpus[%d]\n", + thread_data, tm, m, cpus->map[m]); + } + if (thread_data->overwrite_maps) { + thread_data->overwrite_maps[tm] = &overwrite_mmap[m]; + pr_debug2("thread_data[%p]: ow_maps[%d] -> ow_mmap[%d], cpus[%d]\n", + thread_data, tm, m, cpus->map[m]); + } + tm++; + } + } + + return 0; +} + +static int record__thread_data_init_pollfd(struct record_thread *thread_data, struct evlist *evlist) +{ + int f, tm, pos; + struct mmap *map, *overwrite_map; + + fdarray__init(&thread_data->pollfd, 64); + + for (tm = 0; tm < thread_data->nr_mmaps; tm++) { + map = thread_data->maps ? thread_data->maps[tm] : NULL; + overwrite_map = thread_data->overwrite_maps ? + thread_data->overwrite_maps[tm] : NULL; + + for (f = 0; f < evlist->core.pollfd.nr; f++) { + void *ptr = evlist->core.pollfd.priv[f].ptr; + + if ((map && ptr == map) || (overwrite_map && ptr == overwrite_map)) { + pos = fdarray__dup_entry_from(&thread_data->pollfd, f, + &evlist->core.pollfd); + if (pos < 0) { + pr_err("Failed to duplicate descriptor in thread pollfd\n"); + return pos; + } + pr_debug2("thread_data[%p]: pollfd[%d] <- event_fd=%d\n", + thread_data, pos, evlist->core.pollfd.entries[f].fd); + } + } + } + + return 0; +} + +static void record__free_thread_data(struct record *rec) +{ + int t; + struct record_thread *thread_data = rec->thread_data; + + if (thread_data == NULL) + return; + + for (t = 0; t < rec->nr_threads; t++) { + record__thread_data_close_pipes(&thread_data[t]); + zfree(&thread_data[t].maps); + zfree(&thread_data[t].overwrite_maps); + fdarray__exit(&thread_data[t].pollfd); + } + + zfree(&rec->thread_data); +} + +static int record__alloc_thread_data(struct record *rec, struct evlist *evlist) +{ + int t, ret; + struct record_thread *thread_data; + + rec->thread_data = zalloc(rec->nr_threads * sizeof(*(rec->thread_data))); + if (!rec->thread_data) { + pr_err("Failed to allocate thread data\n"); + return -ENOMEM; + } + thread_data = rec->thread_data; + + for (t = 0; t < rec->nr_threads; t++) + record__thread_data_init_pipes(&thread_data[t]); + + for (t = 0; t < rec->nr_threads; t++) { + thread_data[t].rec = rec; + thread_data[t].mask = &rec->thread_masks[t]; + ret = record__thread_data_init_maps(&thread_data[t], evlist); + if (ret) + goto out_free; + ret = record__thread_data_init_pollfd(&thread_data[t], evlist); + if (ret) { + pr_err("Failed to initialize thread pollfd\n"); + goto out_free; + } + if (t) { + thread_data[t].tid = -1; + ret = record__thread_data_open_pipes(&thread_data[t]); + if (ret) + goto out_free; + thread_data[t].ctlfd_pos = fdarray__add(&thread_data[t].pollfd, + thread_data[t].pipes.msg[0], + POLLIN | POLLERR | POLLHUP, + fdarray_flag__nonfilterable); + if (thread_data[t].ctlfd_pos < 0) { + pr_err("Failed to add descriptor to thread pollfd\n"); + ret = -ENOMEM; + goto out_free; + } + pr_debug2("thread_data[%p]: pollfd[%d] <- ctl_fd=%d\n", + thread_data, thread_data[t].ctlfd_pos, + thread_data[t].pipes.msg[0]); + } else { + thread_data[t].tid = gettid(); + if (evlist->ctl_fd.pos == -1) + continue; + thread_data[t].ctlfd_pos = fdarray__dup_entry_from(&thread_data[t].pollfd, + evlist->ctl_fd.pos, + &evlist->core.pollfd); + if (thread_data[t].ctlfd_pos < 0) { + pr_err("Failed to duplicate descriptor in thread pollfd\n"); + ret = -ENOMEM; + goto out_free; + } + pr_debug2("thread_data[%p]: pollfd[%d] <- ctl_fd=%d\n", + thread_data, thread_data[t].ctlfd_pos, + evlist->core.pollfd.entries[evlist->ctl_fd.pos].fd); + } + } + + return 0; + +out_free: + record__free_thread_data(rec); + + return ret; +} + static int record__mmap_evlist(struct record *rec, struct evlist *evlist) { + int ret; struct record_opts *opts = &rec->opts; bool auxtrace_overwrite = opts->auxtrace_snapshot_mode || opts->auxtrace_sample_mode; @@ -880,6 +1122,14 @@ static int record__mmap_evlist(struct record *rec, return -EINVAL; } } + + if (evlist__initialize_ctlfd(evlist, opts->ctl_fd, opts->ctl_fd_ack)) + return -1; + + ret = record__alloc_thread_data(rec, evlist); + if (ret) + return ret; + return 0; } @@ -1851,9 +2101,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) evlist__start_workload(rec->evlist); } - if (evlist__initialize_ctlfd(rec->evlist, opts->ctl_fd, opts->ctl_fd_ack)) - goto out_child; - if (opts->initial_delay) { pr_info(EVLIST_DISABLED_MSG); if (opts->initial_delay > 0) { @@ -2011,6 +2258,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) out_child: evlist__finalize_ctlfd(rec->evlist); record__mmap_read_all(rec, true); + record__free_thread_data(rec); record__aio_mmap_read_sync(rec); if (rec->session->bytes_transferred && rec->session->bytes_compressed) { -- 2.19.0