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=-16.7 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 051BEC43381 for ; Thu, 11 Feb 2021 13:44:32 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id A181A64E92 for ; Thu, 11 Feb 2021 13:44:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S230314AbhBKNoS (ORCPT ); Thu, 11 Feb 2021 08:44:18 -0500 Received: from foss.arm.com ([217.140.110.172]:52164 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S231968AbhBKNmP (ORCPT ); Thu, 11 Feb 2021 08:42:15 -0500 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 22115142F; Thu, 11 Feb 2021 05:39:40 -0800 (PST) Received: from e121896.arm.com (unknown [10.57.43.88]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 696D53F73B; Thu, 11 Feb 2021 05:39:36 -0800 (PST) From: James Clark To: linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org Cc: Leo Yan , James Clark , Peter Zijlstra , Ingo Molnar , Arnaldo Carvalho de Melo , Mark Rutland , Alexander Shishkin , Jiri Olsa , Namhyung Kim , John Garry , Will Deacon , Mathieu Poirier , Al Grant , Andre Przywara , Wei Li , Adrian Hunter Subject: [PATCH v2 6/6] perf arm-spe: Set sample's data source field Date: Thu, 11 Feb 2021 15:38:56 +0200 Message-Id: <20210211133856.2137-6-james.clark@arm.com> X-Mailer: git-send-email 2.28.0 In-Reply-To: <20210211133856.2137-1-james.clark@arm.com> References: <20210211133856.2137-1-james.clark@arm.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk List-ID: X-Mailing-List: linux-perf-users@vger.kernel.org From: Leo Yan The sample structure contains the field 'data_src' which is used to tell the data operation attributions, e.g. operation type is loading or storing, cache level, it's snooping or remote accessing, etc. At the end, the 'data_src' will be parsed by perf mem/c2c tools to display human readable strings. This patch is to fill the 'data_src' field in the synthesized samples base on different types. Currently perf tool can display statistics for L1/L2/L3 caches but it doesn't support the 'last level cache'. To fit to current implementation, 'data_src' field uses L3 cache for last level cache. Before this commit, perf mem report looks like this: # Samples: 75K of event 'l1d-miss' # Total weight : 75951 # Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked # # Overhead Samples Local Weight Memory access Symbol Shared Object Data Symbol Data Object Snoop TLB access # ........ ............ ............ ........................ ...................... ................ ...................... ................ ............ ................... # 81.56% 61945 0 N/A [.] 0x00000000000009d8 serial_c [.] 0000000000000000 [unknown] N/A N/A 18.44% 14003 0 N/A [.] 0x0000000000000828 serial_c [.] 0000000000000000 [unknown] N/A N/A Now on a system with Arm SPE, addresses and access types are displayed: # Samples: 75K of event 'l1d-miss' # Total weight : 75951 # Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked # # Overhead Samples Local Weight Memory access Symbol Shared Object Data Symbol Data Object Snoop TLB access # ........ ............ ............ ........................ ...................... ................ ...................... ........... ............ ...................... # 0.43% 324 0 L1 miss [.] 0x00000000000009d8 serial_c [.] 0x0000ffff80794e00 anon N/A Walker hit 0.42% 322 0 L1 miss [.] 0x00000000000009d8 serial_c [.] 0x0000ffff80794580 anon N/A Walker hit Signed-off-by: Leo Yan Signed-off-by: James Clark Reviewed-by: James Clark Tested-by: James Clark Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo Cc: Mark Rutland Cc: Alexander Shishkin Cc: Jiri Olsa Cc: Namhyung Kim Cc: John Garry Cc: Will Deacon Cc: Mathieu Poirier Cc: Al Grant Cc: Andre Przywara Cc: Wei Li Cc: Adrian Hunter --- tools/perf/util/arm-spe.c | 69 ++++++++++++++++++++++++++++++++++----- 1 file changed, 60 insertions(+), 9 deletions(-) diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c index 5550906486d8..27a0b9dfe22d 100644 --- a/tools/perf/util/arm-spe.c +++ b/tools/perf/util/arm-spe.c @@ -261,7 +261,7 @@ arm_spe_deliver_synth_event(struct arm_spe *spe, } static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq, - u64 spe_events_id) + u64 spe_events_id, u64 data_src) { struct arm_spe *spe = speq->spe; struct arm_spe_record *record = &speq->decoder->record; @@ -274,6 +274,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq, sample.stream_id = spe_events_id; sample.addr = record->virt_addr; sample.phys_addr = record->phys_addr; + sample.data_src = data_src; return arm_spe_deliver_synth_event(spe, speq, event, &sample); } @@ -307,21 +308,66 @@ static bool arm_spe__is_memory_event(enum arm_spe_sample_type type) return false; } +static u64 arm_spe__synth_data_source(const struct arm_spe_record *record) +{ + union perf_mem_data_src data_src = { 0 }; + + if (record->op == ARM_SPE_LD) + data_src.mem_op = PERF_MEM_OP_LOAD; + else + data_src.mem_op = PERF_MEM_OP_STORE; + + if (record->type & (ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS)) { + data_src.mem_lvl = PERF_MEM_LVL_L3; + + if (record->type & ARM_SPE_LLC_MISS) + data_src.mem_lvl |= PERF_MEM_LVL_MISS; + else + data_src.mem_lvl |= PERF_MEM_LVL_HIT; + } else if (record->type & (ARM_SPE_L1D_ACCESS | ARM_SPE_L1D_MISS)) { + data_src.mem_lvl = PERF_MEM_LVL_L1; + + if (record->type & ARM_SPE_L1D_MISS) + data_src.mem_lvl |= PERF_MEM_LVL_MISS; + else + data_src.mem_lvl |= PERF_MEM_LVL_HIT; + } + + if (record->type & ARM_SPE_REMOTE_ACCESS) + data_src.mem_lvl |= PERF_MEM_LVL_REM_CCE1; + + if (record->type & (ARM_SPE_TLB_ACCESS | ARM_SPE_TLB_MISS)) { + data_src.mem_dtlb = PERF_MEM_TLB_WK; + + if (record->type & ARM_SPE_TLB_MISS) + data_src.mem_dtlb |= PERF_MEM_TLB_MISS; + else + data_src.mem_dtlb |= PERF_MEM_TLB_HIT; + } + + return data_src.val; +} + static int arm_spe_sample(struct arm_spe_queue *speq) { const struct arm_spe_record *record = &speq->decoder->record; struct arm_spe *spe = speq->spe; + u64 data_src; int err; + data_src = arm_spe__synth_data_source(record); + if (spe->sample_flc) { if (record->type & ARM_SPE_L1D_MISS) { - err = arm_spe__synth_mem_sample(speq, spe->l1d_miss_id); + err = arm_spe__synth_mem_sample(speq, spe->l1d_miss_id, + data_src); if (err) return err; } if (record->type & ARM_SPE_L1D_ACCESS) { - err = arm_spe__synth_mem_sample(speq, spe->l1d_access_id); + err = arm_spe__synth_mem_sample(speq, spe->l1d_access_id, + data_src); if (err) return err; } @@ -329,13 +375,15 @@ static int arm_spe_sample(struct arm_spe_queue *speq) if (spe->sample_llc) { if (record->type & ARM_SPE_LLC_MISS) { - err = arm_spe__synth_mem_sample(speq, spe->llc_miss_id); + err = arm_spe__synth_mem_sample(speq, spe->llc_miss_id, + data_src); if (err) return err; } if (record->type & ARM_SPE_LLC_ACCESS) { - err = arm_spe__synth_mem_sample(speq, spe->llc_access_id); + err = arm_spe__synth_mem_sample(speq, spe->llc_access_id, + data_src); if (err) return err; } @@ -343,13 +391,15 @@ static int arm_spe_sample(struct arm_spe_queue *speq) if (spe->sample_tlb) { if (record->type & ARM_SPE_TLB_MISS) { - err = arm_spe__synth_mem_sample(speq, spe->tlb_miss_id); + err = arm_spe__synth_mem_sample(speq, spe->tlb_miss_id, + data_src); if (err) return err; } if (record->type & ARM_SPE_TLB_ACCESS) { - err = arm_spe__synth_mem_sample(speq, spe->tlb_access_id); + err = arm_spe__synth_mem_sample(speq, spe->tlb_access_id, + data_src); if (err) return err; } @@ -363,13 +413,14 @@ static int arm_spe_sample(struct arm_spe_queue *speq) if (spe->sample_remote_access && (record->type & ARM_SPE_REMOTE_ACCESS)) { - err = arm_spe__synth_mem_sample(speq, spe->remote_access_id); + err = arm_spe__synth_mem_sample(speq, spe->remote_access_id, + data_src); if (err) return err; } if (spe->sample_memory && arm_spe__is_memory_event(record->type)) { - err = arm_spe__synth_mem_sample(speq, spe->memory_id); + err = arm_spe__synth_mem_sample(speq, spe->memory_id, data_src); if (err) return err; } -- 2.28.0