Received: by 2002:a25:ab43:0:0:0:0:0 with SMTP id u61csp5436005ybi; Wed, 12 Jun 2019 02:26:56 -0700 (PDT) X-Google-Smtp-Source: APXvYqzepoq6byDR/zYYfR338Lh9NfgW91EixfwR2XEJA3eVvji6LU196OXMDtH855QsnECOZWwB X-Received: by 2002:a62:2506:: with SMTP id l6mr85037014pfl.250.1560331616270; Wed, 12 Jun 2019 02:26:56 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1560331616; cv=none; d=google.com; s=arc-20160816; b=fBH3v3SF2EtcW2IrS2xkV/Dyq6lHcLwuafrXXUeTKZdRRLs1mqacTbVJfmvJM+ReKZ ltvn0rqirfaIo4ly0fZvXEtdSMkb5GeKzxzpp2uc5yn0dGbEm8CrdSKEKs8/Lro7wNhA Ozutl+YMfdmqzTCXzcDCxQmUEEUAZMx6LAfvJ6IOuPoA+duxbMVYl8EPKhj5WDkKGEDd y/LUgbSWMhyZ4tnVJEZuVkPUUMqnfIa3Pmt7q4zOJIrtKUJbVcgxr+wysWNIj2UYWdBc NJ0Vxxcm8nicuTYgtsvSo+wMcO16yoWUcyZgE33C+562lgYVonzHcI2JyFXO4PSAA3kE 5qfQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from; bh=BMM2zd85O7abr9kEmVx2DD2xlXum9T0Yb1AdWb97OjY=; b=oBdV0wQPAX0ieSSy8R5/3SbWaZPMy8lilqYIsNsbOetJPzk3NjoSJrIqzDxDjfFNpi UUgdwIa3Ah9cjMUVrTnKodpZ0a5NTRe5kwBFcLKFb2qzfVG25zikbvh1B/qsCXtOgcoO YpCbBjwZDCXwLt3r75wkX3w1ksXrz2hdg8zJgRbDJptFMK4rbyznalbHuDgwe/stxT6+ Fzb8zNXw114Iftnn+4amNbWIYa5BEVhDCfGt2iwKl45xrGZVs+UD61dhIvp455O4bs/n kI2+WxkCYWJIRqHYinYx6ceviQZ/LTrGcdszPBtUwjxicWeAQjtGV4ncv7jkWGNQ2LDU sp+g== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id j38si14807966pgi.227.2019.06.12.02.26.40; Wed, 12 Jun 2019 02:26:56 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S2437255AbfFLJPC (ORCPT + 99 others); Wed, 12 Jun 2019 05:15:02 -0400 Received: from szxga04-in.huawei.com ([45.249.212.190]:18559 "EHLO huawei.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S2436777AbfFLJPB (ORCPT ); Wed, 12 Jun 2019 05:15:01 -0400 Received: from DGGEMS409-HUB.china.huawei.com (unknown [172.30.72.59]) by Forcepoint Email with ESMTP id 06646C5C9D43BF77E6DD; Wed, 12 Jun 2019 17:11:56 +0800 (CST) Received: from HGHY2Y004646261.china.huawei.com (10.184.12.158) by DGGEMS409-HUB.china.huawei.com (10.3.19.209) with Microsoft SMTP Server id 14.3.439.0; Wed, 12 Jun 2019 17:11:46 +0800 From: Zenghui Yu To: , , , , CC: , , , , , , , , , , , , , , , , Zenghui Yu Subject: [PATCH v1 3/5] perf tools arm64: Add support for get_cpuid() function Date: Wed, 12 Jun 2019 09:08:44 +0000 Message-ID: <1560330526-15468-4-git-send-email-yuzenghui@huawei.com> X-Mailer: git-send-email 2.6.4.windows.1 In-Reply-To: <1560330526-15468-1-git-send-email-yuzenghui@huawei.com> References: <1560330526-15468-1-git-send-email-yuzenghui@huawei.com> MIME-Version: 1.0 Content-Type: text/plain X-Originating-IP: [10.184.12.158] X-CFilter-Loop: Reflected Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The get_cpuid() function returns the MIDR string of the first CPU. Cc: Ganapatrao Kulkarni Cc: Arnaldo Carvalho de Melo Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Catalin Marinas Cc: Will Deacon Cc: Mark Rutland Signed-off-by: Zenghui Yu --- When recording, perf will write host's cpuid (through get_cpuid()) into perf.data.guest file: __cmd_record record__finish_output perf_session__write_header perf_header__adds_write do_write_feat (type == HEADER_CPUID) write_cpuid When reporting, perf will read cpuid from perf.data.guest file: read_events perf_session__new perf_session__open perf_session__read_header perf_header__process_sections perf_file_section__process process_cpuid I'm not familiar with ARM ID register usage, and how does perf code make use of get_cpuid() function. If we left get_cpuid() unimplemented on arm64 (we have a default implementation in tools/perf/util/header.c), 'perf kvm stat report' will failed with following error: "Failed to look up CPU type" I will read the code further, and any comments or suggestions from both sides (arm64 & perf) will be appreciated. --- tools/perf/arch/arm64/util/header.c | 74 +++++++++++++++++++++++-------------- 1 file changed, 47 insertions(+), 27 deletions(-) diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c index 534cd25..5c17b86 100644 --- a/tools/perf/arch/arm64/util/header.c +++ b/tools/perf/arch/arm64/util/header.c @@ -9,17 +9,56 @@ #define MIDR_VARIANT_SHIFT 20 #define MIDR_VARIANT_MASK (0xf << MIDR_VARIANT_SHIFT) -char *get_cpuid_str(struct perf_pmu *pmu) +/* Return value of midr_el1 if success, else return 0. */ +static int read_midr_el1(char *buf, int cpu_nr) { - char *buf = NULL; char path[PATH_MAX]; const char *sysfs = sysfs__mountpoint(); + u64 midr = 0; + FILE *file; + + if (!sysfs) + return 0; + + scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, + sysfs, cpu_nr); + + file = fopen(path, "r"); + if (!file) { + pr_debug("fopen failed for file %s\n", path); + return 0; + } + + if (!fgets(buf, MIDR_SIZE, file)) { + fclose(file); + return 0; + } + fclose(file); + + /* Ignore/clear Variant[23:20] and Revision[3:0] of MIDR */ + midr = strtoul(buf, NULL, 16); + midr &= (~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK)); + scnprintf(buf, MIDR_SIZE, "0x%016lx", midr); + + return midr; +} + +int get_cpuid(char *buffer, size_t sz __maybe_unused) +{ + if (read_midr_el1(buffer, 0)) + return 0; + + return -1; +} + +char *get_cpuid_str(struct perf_pmu *pmu) +{ + char *buf = NULL; int cpu; u64 midr = 0; struct cpu_map *cpus; - FILE *file; - if (!sysfs || !pmu || !pmu->cpus) + if (!pmu || !pmu->cpus) return NULL; buf = malloc(MIDR_SIZE); @@ -29,29 +68,10 @@ char *get_cpuid_str(struct perf_pmu *pmu) /* read midr from list of cpus mapped to this pmu */ cpus = cpu_map__get(pmu->cpus); for (cpu = 0; cpu < cpus->nr; cpu++) { - scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d"MIDR, - sysfs, cpus->map[cpu]); - - file = fopen(path, "r"); - if (!file) { - pr_debug("fopen failed for file %s\n", path); - continue; - } - - if (!fgets(buf, MIDR_SIZE, file)) { - fclose(file); - continue; - } - fclose(file); - - /* Ignore/clear Variant[23:20] and - * Revision[3:0] of MIDR - */ - midr = strtoul(buf, NULL, 16); - midr &= (~(MIDR_VARIANT_MASK | MIDR_REVISION_MASK)); - scnprintf(buf, MIDR_SIZE, "0x%016lx", midr); - /* got midr break loop */ - break; + midr = read_midr_el1(buf, cpus->map[cpu]); + if (midr) + /* got midr break loop */ + break; } if (!midr) { -- 1.8.3.1