Received: by 2002:a25:ad19:0:0:0:0:0 with SMTP id y25csp3784073ybi; Mon, 29 Jul 2019 12:33:24 -0700 (PDT) X-Google-Smtp-Source: APXvYqzy3kIiR+7tw+0aSvM3Kbl7FP5GXn62LK2fQwmQ70UBJMnudH6ELIlUF/wjN+EnIW+n9iaW X-Received: by 2002:a62:5883:: with SMTP id m125mr37905817pfb.248.1564428804049; Mon, 29 Jul 2019 12:33:24 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1564428804; cv=none; d=google.com; s=arc-20160816; b=a1hLqQApeq41o8GKV3gmYL8VZVjKnWGbJr3wEDGqNFk6pMaK+C10eB53X+jtXvT2PU GAyy4O41jxMzoipGenaz7VTmSl1ELF8+0BGyFAEo3FIpl3bHklXVzLckVQNGf3qVp40T TCTxLK/c0DvvGXCx3R51/+gRc5FAXcdggKjPgX1cWK8PkbHn/bW/3lZtayvvCHGEVmzT 3veek48EJU3lBhDiQmFmoKQYmLY43YEyg6DQBEoXTwi5/CLoTuXZvXaL1n9hbvcOIb7o 0v5gDfIuoF0XQunkxD8wh/KWcuj2bHeVPwKnyNBLjq/RGKELzV/N4Yp9LpENeHsZMQQt z7xQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:content-transfer-encoding:mime-version :user-agent:references:in-reply-to:message-id:date:subject:cc:to :from:dkim-signature; bh=V/H6j3DWtp5WdGiOG2bV6GMSfcyE3WWcREOu8doYf2s=; b=sxoWJEMwSD9cpdGhn29IUr9EpZvtro2RBzk/G6IWC+pNogDiqvW1eHOYv0Mbh0mxSk hNIJD+/rvWMUs/DxjRMI3y9P2AdmraH2Wf0AY6KqJtqbJ/WByRAfYKvVBb1eKZ3/AFZb CZiQLNtbR2emmqpGexUH5ZEhsqvL22+7Ojwru2xCBKgkAoqUavNZ84ThZFK57nUIUlXX 46ocO0djqqCo9RqdgC25lBwrwFvqOxxcs5Em+qRC87eXqhs86quVZrbRGrMCCnLZIrgj YtUiI2YoFeYACHvbpKJmQ9oqKXNGapWEsftyMxlfq1PD15gEFt2vKvJfVY8Te6caP5bm NWsw== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@kernel.org header.s=default header.b=B4OqXSR8; 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 j70si27646933pgd.500.2019.07.29.12.33.09; Mon, 29 Jul 2019 12:33:24 -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; dkim=pass header.i=@kernel.org header.s=default header.b=B4OqXSR8; 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 S1729655AbfG2TZc (ORCPT + 99 others); Mon, 29 Jul 2019 15:25:32 -0400 Received: from mail.kernel.org ([198.145.29.99]:37800 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727948AbfG2TZa (ORCPT ); Mon, 29 Jul 2019 15:25:30 -0400 Received: from localhost (83-86-89-107.cable.dynamic.v4.ziggo.nl [83.86.89.107]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id A13CA20C01; Mon, 29 Jul 2019 19:25:28 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1564428329; bh=Y145IE3priBcqqoYz0QQL4y2C4xKM7CgKtqz84vUrBo=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=B4OqXSR86l/MJYrGcSbKNtXFTdRmZynoXRgVxj+Q2fNu/kGHfAohY/1UtsqbP/8ct JDyZ3kaJClB8xTrPVTQPAWDiioL1SlLLWvKvMfYnmIjNbQqMkJ4oav0EULexGcDj1R W45vRKi7Oh/hxa1YEXdlCobwEjzZ0xzSbkSQXXEE= From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Mathieu Poirier , Leo Yan , Alexander Shishkin , Jiri Olsa , Peter Zijlstra , Suzuki Poulouse , linux-arm-kernel@lists.infradead.org, Arnaldo Carvalho de Melo , Sasha Levin Subject: [PATCH 4.14 041/293] perf cs-etm: Properly set the value of old and head in snapshot mode Date: Mon, 29 Jul 2019 21:18:52 +0200 Message-Id: <20190729190825.755944581@linuxfoundation.org> X-Mailer: git-send-email 2.22.0 In-Reply-To: <20190729190820.321094988@linuxfoundation.org> References: <20190729190820.321094988@linuxfoundation.org> User-Agent: quilt/0.66 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org [ Upstream commit e45c48a9a4d20ebc7b639a62c3ef8f4b08007027 ] This patch adds the necessary intelligence to properly compute the value of 'old' and 'head' when operating in snapshot mode. That way we can get the latest information in the AUX buffer and be compatible with the generic AUX ring buffer mechanic. Tester notes: > Leo, have you had the chance to test/review this one? Suzuki? Sure. I applied this patch on the perf/core branch (with latest commit 3e4fbf36c1e3 'perf augmented_raw_syscalls: Move reading filename to the loop') and passed testing with below steps: # perf record -e cs_etm/@tmc_etr0/ -S -m,64 --per-thread ./sort & [1] 19097 Bubble sorting array of 30000 elements # kill -USR2 19097 # kill -USR2 19097 # kill -USR2 19097 [ perf record: Woken up 4 times to write data ] [ perf record: Captured and wrote 0.753 MB perf.data ] Signed-off-by: Mathieu Poirier Tested-by: Leo Yan Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Peter Zijlstra Cc: Suzuki Poulouse Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/20190605161633.12245-1-mathieu.poirier@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin --- tools/perf/arch/arm/util/cs-etm.c | 127 +++++++++++++++++++++++++++++- 1 file changed, 123 insertions(+), 4 deletions(-) diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c index fbfc055d3f4d..aec62e822bab 100644 --- a/tools/perf/arch/arm/util/cs-etm.c +++ b/tools/perf/arch/arm/util/cs-etm.c @@ -43,6 +43,8 @@ struct cs_etm_recording { struct auxtrace_record itr; struct perf_pmu *cs_etm_pmu; struct perf_evlist *evlist; + int wrapped_cnt; + bool *wrapped; bool snapshot_mode; size_t snapshot_size; }; @@ -485,16 +487,131 @@ static int cs_etm_info_fill(struct auxtrace_record *itr, return 0; } -static int cs_etm_find_snapshot(struct auxtrace_record *itr __maybe_unused, +static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx) +{ + bool *wrapped; + int cnt = ptr->wrapped_cnt; + + /* Make @ptr->wrapped as big as @idx */ + while (cnt <= idx) + cnt++; + + /* + * Free'ed in cs_etm_recording_free(). Using realloc() to avoid + * cross compilation problems where the host's system supports + * reallocarray() but not the target. + */ + wrapped = realloc(ptr->wrapped, cnt * sizeof(bool)); + if (!wrapped) + return -ENOMEM; + + wrapped[cnt - 1] = false; + ptr->wrapped_cnt = cnt; + ptr->wrapped = wrapped; + + return 0; +} + +static bool cs_etm_buffer_has_wrapped(unsigned char *buffer, + size_t buffer_size, u64 head) +{ + u64 i, watermark; + u64 *buf = (u64 *)buffer; + size_t buf_size = buffer_size; + + /* + * We want to look the very last 512 byte (chosen arbitrarily) in + * the ring buffer. + */ + watermark = buf_size - 512; + + /* + * @head is continuously increasing - if its value is equal or greater + * than the size of the ring buffer, it has wrapped around. + */ + if (head >= buffer_size) + return true; + + /* + * The value of @head is somewhere within the size of the ring buffer. + * This can be that there hasn't been enough data to fill the ring + * buffer yet or the trace time was so long that @head has numerically + * wrapped around. To find we need to check if we have data at the very + * end of the ring buffer. We can reliably do this because mmap'ed + * pages are zeroed out and there is a fresh mapping with every new + * session. + */ + + /* @head is less than 512 byte from the end of the ring buffer */ + if (head > watermark) + watermark = head; + + /* + * Speed things up by using 64 bit transactions (see "u64 *buf" above) + */ + watermark >>= 3; + buf_size >>= 3; + + /* + * If we find trace data at the end of the ring buffer, @head has + * been there and has numerically wrapped around at least once. + */ + for (i = watermark; i < buf_size; i++) + if (buf[i]) + return true; + + return false; +} + +static int cs_etm_find_snapshot(struct auxtrace_record *itr, int idx, struct auxtrace_mmap *mm, - unsigned char *data __maybe_unused, + unsigned char *data, u64 *head, u64 *old) { + int err; + bool wrapped; + struct cs_etm_recording *ptr = + container_of(itr, struct cs_etm_recording, itr); + + /* + * Allocate memory to keep track of wrapping if this is the first + * time we deal with this *mm. + */ + if (idx >= ptr->wrapped_cnt) { + err = cs_etm_alloc_wrapped_array(ptr, idx); + if (err) + return err; + } + + /* + * Check to see if *head has wrapped around. If it hasn't only the + * amount of data between *head and *old is snapshot'ed to avoid + * bloating the perf.data file with zeros. But as soon as *head has + * wrapped around the entire size of the AUX ring buffer it taken. + */ + wrapped = ptr->wrapped[idx]; + if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) { + wrapped = true; + ptr->wrapped[idx] = true; + } + pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n", __func__, idx, (size_t)*old, (size_t)*head, mm->len); - *old = *head; - *head += mm->len; + /* No wrap has occurred, we can just use *head and *old. */ + if (!wrapped) + return 0; + + /* + * *head has wrapped around - adjust *head and *old to pickup the + * entire content of the AUX buffer. + */ + if (*head >= mm->len) { + *old = *head - mm->len; + } else { + *head += mm->len; + *old = *head - mm->len; + } return 0; } @@ -535,6 +652,8 @@ static void cs_etm_recording_free(struct auxtrace_record *itr) { struct cs_etm_recording *ptr = container_of(itr, struct cs_etm_recording, itr); + + zfree(&ptr->wrapped); free(ptr); } -- 2.20.1