From nobody Mon Dec 29 20:11:01 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 254A4C624B4 for ; Thu, 23 Nov 2023 12:19:24 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1345275AbjKWMTP (ORCPT ); Thu, 23 Nov 2023 07:19:15 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:41326 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1345278AbjKWMTN (ORCPT ); Thu, 23 Nov 2023 07:19:13 -0500 Received: from mgamail.intel.com (mgamail.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id B3B9A1B6; Thu, 23 Nov 2023 04:19:18 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1700741958; x=1732277958; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=9eVm6Qcu6ibP2mSqWgj5H5xz5zeq8ashdLYRfy2nUaY=; b=jkvIP56D2K7LP0vKWZ1iNWBNkgSbpPEPl3NlkPsC6WSs8KGNODmZcZP+ 5koHWbPWBN2YY0EjRYSfOFIlI/JZlykRMCCBWm6KrOqkXwV66WHSZXSfI nVVX2zx0xnKMDIcAN9VfJBCPZsks1T5GLVVe1ayqgXyOIEmsmW9HsOsyG 1sZMPm3XiDdWE3rTiuXvRoQyCsMKrgJpIOnxZ9lLVkfhRpAiyt7SYdYbx 3cCV7XKRdRmXbjHqNV/ZvcnJWuqsApxBgDKcWf8TqdkZE5c0p2r0inMLp 5xNBKW5to407GqI7jieUoBqbQAfzN3blSBrfmmHtcmxzIhTEhnBVIkbdi Q==; X-IronPort-AV: E=McAfee;i="6600,9927,10902"; a="478456339" X-IronPort-AV: E=Sophos;i="6.04,221,1695711600"; d="scan'208";a="478456339" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 23 Nov 2023 04:19:18 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10902"; a="890774787" X-IronPort-AV: E=Sophos;i="6.04,221,1695711600"; d="scan'208";a="890774787" Received: from ahunter6-mobl1.ger.corp.intel.com (HELO ahunter-VirtualBox.home\044ger.corp.intel.com) ([10.252.41.107]) by orsmga004-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 23 Nov 2023 04:19:12 -0800 From: Adrian Hunter To: Peter Zijlstra Cc: Ingo Molnar , Mark Rutland , Alexander Shishkin , Heiko Carstens , Thomas Richter , Hendrik Brueckner , Suzuki K Poulose , Mike Leach , James Clark , coresight@lists.linaro.org, linux-arm-kernel@lists.infradead.org, Yicong Yang , Jonathan Cameron , Will Deacon , Arnaldo Carvalho de Melo , Jiri Olsa , Namhyung Kim , Ian Rogers , linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org Subject: [PATCH RFC 1/3] perf/core: Add aux_pause, aux_resume, aux_start_paused Date: Thu, 23 Nov 2023 14:18:49 +0200 Message-Id: <20231123121851.10826-2-adrian.hunter@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20231123121851.10826-1-adrian.hunter@intel.com> References: <20231123121851.10826-1-adrian.hunter@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy, Registered Address: PL 281, 00181 Helsinki, Business Identity Code: 0357606 - 4, Domiciled in Helsinki Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Hardware traces, such as instruction traces, can produce a vast amount of trace data, so being able to reduce tracing to more specific circumstances can be useful. The ability to pause or resume tracing when another event happens, can do that. Add ability for an event to "pause" or "resume" AUX area tracing. Add aux_pause bit to perf_event_attr to indicate that, if the event happens, the associated AUX area tracing should be paused. Ditto aux_resume. Do not allow aux_pause and aux_resume to be set together. Add aux_start_paused bit to perf_event_attr to indicate to an AUX area event that it should start in a "paused" state. Add aux_paused to struct perf_event for AUX area events to keep track of the "paused" state. aux_paused is initialized to aux_start_paused. Add pause_resume() callback to struct pmu to perform a pause or resume. Whether to pause or resume is indicated by aux_paused. Call pause_resume() as needed, during __perf_event_output(). Add aux_in_pause_resume to struct perf_buffer to prevent races with the NMI handler. Pause/resume in NMI context will miss out if it coinicides with another pause/resume. To use aux_pause or aux_resume, an event must be in a group with the AUX area event as the group leader. Example (requires Intel PT and tools patches also): $ perf record --kcore -e '{intel_pt/aux-start-paused/k,syscalls:sys_enter_= newuname/aux-resume/,syscalls:sys_exit_newuname/aux-pause/}' uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.041 MB perf.data ] $ perf script --call-trace uname 8866 [003] 1549.674345648: name: 0x7fff01491a90 uname 8866 [003] 1549.674347393: psb offs: 0 uname 8866 [003] 1549.674347393: cbr: 47 freq: 4705 MHz (168%) uname 8866 [003] 1549.674347556: ([kernel.kallsyms]) debug_smp_= processor_id uname 8866 [003] 1549.674347556: ([kernel.kallsyms]) __x64_sys_= newuname uname 8866 [003] 1549.674347556: ([kernel.kallsyms]) down_r= ead uname 8866 [003] 1549.674347556: ([kernel.kallsyms]) __= cond_resched uname 8866 [003] 1549.674347764: ([kernel.kallsyms]) pr= eempt_count_add uname 8866 [003] 1549.674347764: ([kernel.kallsyms]) = in_lock_functions uname 8866 [003] 1549.674347764: ([kernel.kallsyms]) pr= eempt_count_sub uname 8866 [003] 1549.674347764: ([kernel.kallsyms]) up_read uname 8866 [003] 1549.674347764: ([kernel.kallsyms]) pr= eempt_count_add uname 8866 [003] 1549.674348181: ([kernel.kallsyms]) = in_lock_functions uname 8866 [003] 1549.674348181: ([kernel.kallsyms]) pr= eempt_count_sub uname 8866 [003] 1549.674348181: ([kernel.kallsyms]) _copy_= to_user uname 8866 [003] 1549.674348181: ([kernel.kallsyms]) syscall_ex= it_to_user_mode uname 8866 [003] 1549.674348181: ([kernel.kallsyms]) syscal= l_exit_work uname 8866 [003] 1549.674348181: ([kernel.kallsyms]) pe= rf_syscall_exit uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = debug_smp_processor_id uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = perf_trace_buf_alloc uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = perf_swevent_get_recursion_context uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = debug_smp_processor_id uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = debug_smp_processor_id uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = perf_tp_event uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = perf_trace_buf_update uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = tracing_gen_ctx_irq_test uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = perf_swevent_event uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = __perf_event_account_interrupt uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = __this_cpu_preempt_check uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = perf_event_output_forward uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = perf_event_aux_pause.part.0 uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = ring_buffer_get uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = __rcu_read_lock uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = __rcu_read_unlock uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = pt_event_pause_resume uname 8866 [003] 1549.674348389: ([kernel.kallsyms]) = debug_smp_processor_id uname 8866 [003] 1549.674348598: ([kernel.kallsyms]) = native_write_msr uname 8866 [003] 1549.674348598: ([kernel.kallsyms]) = native_write_msr uname 8866 [003] 1549.674348869: 0x0 Signed-off-by: Adrian Hunter --- include/linux/perf_event.h | 9 +++++ include/uapi/linux/perf_event.h | 13 ++++++- kernel/events/core.c | 65 +++++++++++++++++++++++++++++++-- kernel/events/internal.h | 1 + 4 files changed, 83 insertions(+), 5 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index e85cd1c0eaf3..1e09d537ff77 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -540,6 +540,12 @@ struct pmu { * Check period value for PERF_EVENT_IOC_PERIOD ioctl. */ int (*check_period) (struct perf_event *event, u64 value); /* optional */ + + /* + * Pause or resume tracing. Used for AUX area tracing. event->aux_paused + * indicates whether tracing should be paused, or otherwise resumed. + */ + void (*pause_resume) (struct perf_event *event); /* optional */ }; =20 enum perf_addr_filter_action_t { @@ -797,6 +803,9 @@ struct perf_event { /* for aux_output events */ struct perf_event *aux_event; =20 + /* for AUX area events */ + unsigned int aux_paused; + void (*destroy)(struct perf_event *); struct rcu_head rcu_head; =20 diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_even= t.h index 39c6a250dd1b..1232e70adfba 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -456,7 +456,8 @@ struct perf_event_attr { inherit_thread : 1, /* children only inherit if cloned with CLONE_THR= EAD */ remove_on_exec : 1, /* event is removed from task on exec */ sigtrap : 1, /* send synchronous SIGTRAP on event */ - __reserved_1 : 26; + aux_start_paused : 1, /* start AUX area tracing paused */ + __reserved_1 : 25; =20 union { __u32 wakeup_events; /* wakeup every n events */ @@ -507,7 +508,15 @@ struct perf_event_attr { __u16 sample_max_stack; __u16 __reserved_2; __u32 aux_sample_size; - __u32 __reserved_3; + + union { + __u32 aux_output_cfg; + struct { + __u64 aux_pause : 1, /* on overflow, pause AUX area tracing */ + aux_resume : 1, /* on overflow, resume AUX area tracing */ + __reserved_3 : 30; + }; + }; =20 /* * User provided data if sigtrap=3D1, passed back to user via diff --git a/kernel/events/core.c b/kernel/events/core.c index 4c72a41f11af..8ec72f9153b7 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -2060,7 +2060,13 @@ static void perf_put_aux_event(struct perf_event *ev= ent) =20 static bool perf_need_aux_event(struct perf_event *event) { - return !!event->attr.aux_output || !!event->attr.aux_sample_size; + return event->attr.aux_output || event->attr.aux_output_cfg || + event->attr.aux_sample_size; +} + +static bool has_aux_pause_resume(struct perf_event *event) +{ + return has_aux(event) && event->pmu->pause_resume; } =20 static int perf_get_aux_event(struct perf_event *event, @@ -2085,6 +2091,10 @@ static int perf_get_aux_event(struct perf_event *eve= nt, !perf_aux_output_match(event, group_leader)) return 0; =20 + if ((event->attr.aux_pause || event->attr.aux_resume) && + !has_aux_pause_resume(group_leader)) + return 0; + if (event->attr.aux_sample_size && !group_leader->pmu->snapshot_aux) return 0; =20 @@ -7773,6 +7783,36 @@ void perf_prepare_header(struct perf_event_header *h= eader, WARN_ON_ONCE(header->size & 7); } =20 +static void perf_event_aux_pause(struct perf_event *event, bool pause) +{ + struct perf_buffer *rb; + unsigned long flags; + + if (WARN_ON_ONCE(!event)) + return; + + if ((pause && event->aux_paused) || (!pause && !event->aux_paused)) + return; + + rb =3D ring_buffer_get(event); + if (!rb) + return; + + local_irq_save(flags); + /* Guard against NMI, NMI loses here */ + if (READ_ONCE(rb->aux_in_pause_resume)) + goto out_restore; + WRITE_ONCE(rb->aux_in_pause_resume, 1); + barrier(); + event->aux_paused =3D pause; + event->pmu->pause_resume(event); + barrier(); + WRITE_ONCE(rb->aux_in_pause_resume, 0); +out_restore: + local_irq_restore(flags); + ring_buffer_put(rb); +} + static __always_inline int __perf_event_output(struct perf_event *event, struct perf_sample_data *data, @@ -7786,6 +7826,9 @@ __perf_event_output(struct perf_event *event, struct perf_event_header header; int err; =20 + if (event->attr.aux_pause) + perf_event_aux_pause(event->aux_event, true); + /* protect the callchain buffers */ rcu_read_lock(); =20 @@ -7802,6 +7845,10 @@ __perf_event_output(struct perf_event *event, =20 exit: rcu_read_unlock(); + + if (event->attr.aux_resume) + perf_event_aux_pause(event->aux_event, false); + return err; } =20 @@ -11941,10 +11988,22 @@ perf_event_alloc(struct perf_event_attr *attr, in= t cpu, } =20 if (event->attr.aux_output && - !(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT)) { + (!(pmu->capabilities & PERF_PMU_CAP_AUX_OUTPUT) || + event->attr.aux_pause || event->attr.aux_resume)) { + err =3D -EOPNOTSUPP; + goto err_pmu; + } + + if (event->attr.aux_pause && event->attr.aux_resume) { + err =3D -EINVAL; + goto err_pmu; + } + + if (event->attr.aux_start_paused && !has_aux_pause_resume(event)) { err =3D -EOPNOTSUPP; goto err_pmu; } + event->aux_paused =3D event->attr.aux_start_paused; =20 if (cgroup_fd !=3D -1) { err =3D perf_cgroup_connect(cgroup_fd, event, attr, group_leader); @@ -12741,7 +12800,7 @@ perf_event_create_kernel_counter(struct perf_event_= attr *attr, int cpu, * Grouping is not supported for kernel events, neither is 'AUX', * make sure the caller's intentions are adjusted. */ - if (attr->aux_output) + if (attr->aux_output || attr->aux_output_cfg) return ERR_PTR(-EINVAL); =20 event =3D perf_event_alloc(attr, cpu, task, NULL, NULL, diff --git a/kernel/events/internal.h b/kernel/events/internal.h index 5150d5f84c03..3320f78117dc 100644 --- a/kernel/events/internal.h +++ b/kernel/events/internal.h @@ -51,6 +51,7 @@ struct perf_buffer { void (*free_aux)(void *); refcount_t aux_refcount; int aux_in_sampling; + int aux_in_pause_resume; void **aux_pages; void *aux_priv; =20 --=20 2.34.1 From nobody Mon Dec 29 20:11:01 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 67BC6C5AD4C for ; Thu, 23 Nov 2023 12:19:30 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1345294AbjKWMTW (ORCPT ); Thu, 23 Nov 2023 07:19:22 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:41408 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1345280AbjKWMTR (ORCPT ); Thu, 23 Nov 2023 07:19:17 -0500 Received: from mgamail.intel.com (mgamail.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id F20F1D42; Thu, 23 Nov 2023 04:19:23 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1700741964; x=1732277964; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=8aCNwpSFHAyXWSCRr6tTvoejhaLHrQ0RcXndxzv80fA=; b=gWMCoVhCK77yAS/boOmjr8CBHR3C6EJ8rUVhE0PkIexL+VjjCH380kZ1 hZ2fpRnkQqOTrgdfnLdYUTiRf9Q7qqdJFOjdDUSr/rvCPjXBcYg2uMsaj ekb2K6iS6i8bAxCnERhOvArnT1/2Mp3d2Vp9prxB9Yh0PZQVSo4cbrAYe BGko5U4gRsPkYesaQs6YYgNBScjHi7oxddftAuRFkXJXAPDwz5UyxAttY yFkrzbIKT631k/F/IsW1iN/5KACb4X9CVO2BLCU+e+zd1J0tNxcKUrl3i SnS1TKPH9P1EMbdO+vShL4fyaNGGPNRWlwkyruUq8zHUWLF0zGUDAn+Xa A==; X-IronPort-AV: E=McAfee;i="6600,9927,10902"; a="478456361" X-IronPort-AV: E=Sophos;i="6.04,221,1695711600"; d="scan'208";a="478456361" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 23 Nov 2023 04:19:23 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10902"; a="890774792" X-IronPort-AV: E=Sophos;i="6.04,221,1695711600"; d="scan'208";a="890774792" Received: from ahunter6-mobl1.ger.corp.intel.com (HELO ahunter-VirtualBox.home\044ger.corp.intel.com) ([10.252.41.107]) by orsmga004-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 23 Nov 2023 04:19:18 -0800 From: Adrian Hunter To: Peter Zijlstra Cc: Ingo Molnar , Mark Rutland , Alexander Shishkin , Heiko Carstens , Thomas Richter , Hendrik Brueckner , Suzuki K Poulose , Mike Leach , James Clark , coresight@lists.linaro.org, linux-arm-kernel@lists.infradead.org, Yicong Yang , Jonathan Cameron , Will Deacon , Arnaldo Carvalho de Melo , Jiri Olsa , Namhyung Kim , Ian Rogers , linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org Subject: [PATCH RFC 2/3] perf/x86/intel/pt: Add support for pause_resume() Date: Thu, 23 Nov 2023 14:18:50 +0200 Message-Id: <20231123121851.10826-3-adrian.hunter@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20231123121851.10826-1-adrian.hunter@intel.com> References: <20231123121851.10826-1-adrian.hunter@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy, Registered Address: PL 281, 00181 Helsinki, Business Identity Code: 0357606 - 4, Domiciled in Helsinki Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Prevent tracing to start if aux_paused. Implement pause_resume() callback. When aux_paused, stop tracing. When not aux_paused, only start tracing if it isn't currently meant to be stopped. Signed-off-by: Adrian Hunter --- arch/x86/events/intel/pt.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c index 42a55794004a..aa883b64814a 100644 --- a/arch/x86/events/intel/pt.c +++ b/arch/x86/events/intel/pt.c @@ -418,6 +418,9 @@ static void pt_config_start(struct perf_event *event) struct pt *pt =3D this_cpu_ptr(&pt_ctx); u64 ctl =3D event->hw.config; =20 + if (event->aux_paused) + return; + ctl |=3D RTIT_CTL_TRACEEN; if (READ_ONCE(pt->vmx_on)) perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL); @@ -1563,6 +1566,14 @@ EXPORT_SYMBOL_GPL(intel_pt_handle_vmx); * PMU callbacks */ =20 +static void pt_event_pause_resume(struct perf_event *event) +{ + if (event->aux_paused) + pt_config_stop(event); + else if (!event->hw.state) + pt_config_start(event); +} + static void pt_event_start(struct perf_event *event, int mode) { struct hw_perf_event *hwc =3D &event->hw; @@ -1798,6 +1809,7 @@ static __init int pt_init(void) pt_pmu.pmu.del =3D pt_event_del; pt_pmu.pmu.start =3D pt_event_start; pt_pmu.pmu.stop =3D pt_event_stop; + pt_pmu.pmu.pause_resume =3D pt_event_pause_resume; pt_pmu.pmu.snapshot_aux =3D pt_event_snapshot_aux; pt_pmu.pmu.read =3D pt_event_read; pt_pmu.pmu.setup_aux =3D pt_buffer_setup_aux; --=20 2.34.1 From nobody Mon Dec 29 20:11:01 2025 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id B9FABC5AD4C for ; Thu, 23 Nov 2023 12:19:36 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1345285AbjKWMT2 (ORCPT ); Thu, 23 Nov 2023 07:19:28 -0500 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:41510 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1345280AbjKWMTY (ORCPT ); Thu, 23 Nov 2023 07:19:24 -0500 Received: from mgamail.intel.com (mgamail.intel.com [192.55.52.43]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id D1073D5A; Thu, 23 Nov 2023 04:19:29 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1700741969; x=1732277969; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=TIU+ctyY7T0Dm2BKv9x90SOWIq3L+Uv2b+dP3ZlXN3E=; b=CbjviqmF4tHw0hb1qBZyEh0oh25Je0C0NNqM9lnjGixpnp0kUrDo6rFb YD1k1fi+NJKpwE8chvZZTBRulvxHuvaVJb6eo5E6K18U8IoxFNsFvuU8y NlrwKDOPFiKWrNh2QcopsABg8jz2Dmm1z5Gz+cebN9kU80H33jbI8AJat mUWYNJYiIVHjyvBkahdyaWmWrRhTiK5texbc1w37IwvnOYv6C5pbbWiZz 6EuoKQAnI56Y6aK4LHLTaW3VxmNhxKQjEcvkemPYjaqQZZW8AF1591ncN QopOhxGGDxTwqY4EBlGD3LQx6wY2y00cp2XFd6D1perF+FVx5Cbqyxjnr Q==; X-IronPort-AV: E=McAfee;i="6600,9927,10902"; a="478456374" X-IronPort-AV: E=Sophos;i="6.04,221,1695711600"; d="scan'208";a="478456374" Received: from orsmga004.jf.intel.com ([10.7.209.38]) by fmsmga105.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 23 Nov 2023 04:19:29 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10902"; a="890774796" X-IronPort-AV: E=Sophos;i="6.04,221,1695711600"; d="scan'208";a="890774796" Received: from ahunter6-mobl1.ger.corp.intel.com (HELO ahunter-VirtualBox.home\044ger.corp.intel.com) ([10.252.41.107]) by orsmga004-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 23 Nov 2023 04:19:23 -0800 From: Adrian Hunter To: Peter Zijlstra Cc: Ingo Molnar , Mark Rutland , Alexander Shishkin , Heiko Carstens , Thomas Richter , Hendrik Brueckner , Suzuki K Poulose , Mike Leach , James Clark , coresight@lists.linaro.org, linux-arm-kernel@lists.infradead.org, Yicong Yang , Jonathan Cameron , Will Deacon , Arnaldo Carvalho de Melo , Jiri Olsa , Namhyung Kim , Ian Rogers , linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org Subject: [PATCH RFC 3/3] perf tools: Add support for AUX area pause_resume() Date: Thu, 23 Nov 2023 14:18:51 +0200 Message-Id: <20231123121851.10826-4-adrian.hunter@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20231123121851.10826-1-adrian.hunter@intel.com> References: <20231123121851.10826-1-adrian.hunter@intel.com> MIME-Version: 1.0 Organization: Intel Finland Oy, Registered Address: PL 281, 00181 Helsinki, Business Identity Code: 0357606 - 4, Domiciled in Helsinki Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Add config terms aux-pause, aux-resume and aux-start-paused. Still to do: validation, fallbacks for perf_event_open, documentation. Signed-off-by: Adrian Hunter --- tools/include/uapi/linux/perf_event.h | 13 +++++++-- tools/perf/util/auxtrace.c | 4 +++ tools/perf/util/evsel.c | 9 +++++++ tools/perf/util/evsel_config.h | 6 +++++ tools/perf/util/parse-events.c | 33 +++++++++++++++++++++++ tools/perf/util/parse-events.h | 3 +++ tools/perf/util/parse-events.l | 3 +++ tools/perf/util/perf_event_attr_fprintf.c | 3 +++ 8 files changed, 72 insertions(+), 2 deletions(-) diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/lin= ux/perf_event.h index 3a64499b0f5d..eebd289b22d7 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -460,7 +460,8 @@ struct perf_event_attr { inherit_thread : 1, /* children only inherit if cloned with CLONE_THR= EAD */ remove_on_exec : 1, /* event is removed from task on exec */ sigtrap : 1, /* send synchronous SIGTRAP on event */ - __reserved_1 : 26; + aux_start_paused : 1, /* start AUX area tracing paused */ + __reserved_1 : 25; =20 union { __u32 wakeup_events; /* wakeup every n events */ @@ -511,7 +512,15 @@ struct perf_event_attr { __u16 sample_max_stack; __u16 __reserved_2; __u32 aux_sample_size; - __u32 __reserved_3; + + union { + __u32 aux_output_cfg; + struct { + __u64 aux_pause : 1, /* on overflow, pause AUX area tracing */ + aux_resume : 1, /* on overflow, resume AUX area tracing */ + __reserved_3 : 30; + }; + }; =20 /* * User provided data if sigtrap=3D1, passed back to user via diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index a0368202a746..4a7ca8b0d100 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -814,6 +814,10 @@ void auxtrace_regroup_aux_output(struct evlist *evlist) if (evsel__is_aux_event(evsel)) aux_evsel =3D evsel; term =3D evsel__get_config_term(evsel, AUX_OUTPUT); + if (!term) + term =3D evsel__get_config_term(evsel, AUX_PAUSE); + if (!term) + term =3D evsel__get_config_term(evsel, AUX_RESUME); /* If possible, group with the AUX event */ if (term && aux_evsel) evlist__regroup(evlist, aux_evsel, evsel); diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index a5da74e3a517..03553c104954 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -1001,6 +1001,15 @@ static void evsel__apply_config_terms(struct evsel *= evsel, case EVSEL__CONFIG_TERM_AUX_OUTPUT: attr->aux_output =3D term->val.aux_output ? 1 : 0; break; + case EVSEL__CONFIG_TERM_AUX_PAUSE: + attr->aux_pause =3D term->val.aux_pause ? 1 : 0; + break; + case EVSEL__CONFIG_TERM_AUX_RESUME: + attr->aux_resume =3D term->val.aux_resume ? 1 : 0; + break; + case EVSEL__CONFIG_TERM_AUX_START_PAUSED: + attr->aux_start_paused =3D term->val.aux_start_paused ? 1 : 0; + break; case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: /* Already applied by auxtrace */ break; diff --git a/tools/perf/util/evsel_config.h b/tools/perf/util/evsel_config.h index aee6f808b512..85ad183b5637 100644 --- a/tools/perf/util/evsel_config.h +++ b/tools/perf/util/evsel_config.h @@ -25,6 +25,9 @@ enum evsel_term_type { EVSEL__CONFIG_TERM_BRANCH, EVSEL__CONFIG_TERM_PERCORE, EVSEL__CONFIG_TERM_AUX_OUTPUT, + EVSEL__CONFIG_TERM_AUX_PAUSE, + EVSEL__CONFIG_TERM_AUX_RESUME, + EVSEL__CONFIG_TERM_AUX_START_PAUSED, EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE, EVSEL__CONFIG_TERM_CFG_CHG, }; @@ -44,6 +47,9 @@ struct evsel_config_term { unsigned long max_events; bool percore; bool aux_output; + bool aux_pause; + bool aux_resume; + bool aux_start_paused; u32 aux_sample_size; u64 cfg_chg; char *str; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index aa2f5c6fc7fc..615b04d5fb30 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -768,6 +768,9 @@ static const char *config_term_name(enum parse_events__= term_type term_type) [PARSE_EVENTS__TERM_TYPE_DRV_CFG] =3D "driver-config", [PARSE_EVENTS__TERM_TYPE_PERCORE] =3D "percore", [PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT] =3D "aux-output", + [PARSE_EVENTS__TERM_TYPE_AUX_PAUSE] =3D "aux-pause", + [PARSE_EVENTS__TERM_TYPE_AUX_RESUME] =3D "aux-resume", + [PARSE_EVENTS__TERM_TYPE_AUX_START_PAUSED] =3D "aux-start-paused", [PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE] =3D "aux-sample-size", [PARSE_EVENTS__TERM_TYPE_METRIC_ID] =3D "metric-id", [PARSE_EVENTS__TERM_TYPE_RAW] =3D "raw", @@ -817,6 +820,9 @@ config_term_avail(enum parse_events__term_type term_typ= e, struct parse_events_er case PARSE_EVENTS__TERM_TYPE_OVERWRITE: case PARSE_EVENTS__TERM_TYPE_DRV_CFG: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_PAUSE: + case PARSE_EVENTS__TERM_TYPE_AUX_RESUME: + case PARSE_EVENTS__TERM_TYPE_AUX_START_PAUSED: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: case PARSE_EVENTS__TERM_TYPE_RAW: case PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE: @@ -936,6 +942,15 @@ do { \ case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: CHECK_TYPE_VAL(NUM); break; + case PARSE_EVENTS__TERM_TYPE_AUX_PAUSE: + CHECK_TYPE_VAL(NUM); + break; + case PARSE_EVENTS__TERM_TYPE_AUX_RESUME: + CHECK_TYPE_VAL(NUM); + break; + case PARSE_EVENTS__TERM_TYPE_AUX_START_PAUSED: + CHECK_TYPE_VAL(NUM); + break; case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: CHECK_TYPE_VAL(NUM); if (term->val.num > UINT_MAX) { @@ -1036,6 +1051,9 @@ static int config_term_tracepoint(struct perf_event_a= ttr *attr, case PARSE_EVENTS__TERM_TYPE_OVERWRITE: case PARSE_EVENTS__TERM_TYPE_NOOVERWRITE: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_PAUSE: + case PARSE_EVENTS__TERM_TYPE_AUX_RESUME: + case PARSE_EVENTS__TERM_TYPE_AUX_START_PAUSED: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: return config_term_common(attr, term, err); case PARSE_EVENTS__TERM_TYPE_USER: @@ -1170,6 +1188,18 @@ do { \ ADD_CONFIG_TERM_VAL(AUX_OUTPUT, aux_output, term->val.num ? 1 : 0, term->weak); break; + case PARSE_EVENTS__TERM_TYPE_AUX_PAUSE: + ADD_CONFIG_TERM_VAL(AUX_PAUSE, aux_pause, + term->val.num ? 1 : 0, term->weak); + break; + case PARSE_EVENTS__TERM_TYPE_AUX_RESUME: + ADD_CONFIG_TERM_VAL(AUX_RESUME, aux_resume, + term->val.num ? 1 : 0, term->weak); + break; + case PARSE_EVENTS__TERM_TYPE_AUX_START_PAUSED: + ADD_CONFIG_TERM_VAL(AUX_START_PAUSED, aux_start_paused, + term->val.num ? 1 : 0, term->weak); + break; case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: ADD_CONFIG_TERM_VAL(AUX_SAMPLE_SIZE, aux_sample_size, term->val.num, term->weak); @@ -1232,6 +1262,9 @@ static int get_config_chgs(struct perf_pmu *pmu, stru= ct parse_events_terms *head case PARSE_EVENTS__TERM_TYPE_DRV_CFG: case PARSE_EVENTS__TERM_TYPE_PERCORE: case PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT: + case PARSE_EVENTS__TERM_TYPE_AUX_PAUSE: + case PARSE_EVENTS__TERM_TYPE_AUX_RESUME: + case PARSE_EVENTS__TERM_TYPE_AUX_START_PAUSED: case PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE: case PARSE_EVENTS__TERM_TYPE_METRIC_ID: case PARSE_EVENTS__TERM_TYPE_RAW: diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h index 63c0a36a4bf1..ff0871385b50 100644 --- a/tools/perf/util/parse-events.h +++ b/tools/perf/util/parse-events.h @@ -74,6 +74,9 @@ enum parse_events__term_type { PARSE_EVENTS__TERM_TYPE_DRV_CFG, PARSE_EVENTS__TERM_TYPE_PERCORE, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT, + PARSE_EVENTS__TERM_TYPE_AUX_PAUSE, + PARSE_EVENTS__TERM_TYPE_AUX_RESUME, + PARSE_EVENTS__TERM_TYPE_AUX_START_PAUSED, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE, PARSE_EVENTS__TERM_TYPE_METRIC_ID, PARSE_EVENTS__TERM_TYPE_RAW, diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l index e86c45675e1d..56963013c3af 100644 --- a/tools/perf/util/parse-events.l +++ b/tools/perf/util/parse-events.l @@ -244,6 +244,9 @@ overwrite { return term(yyscanner, PARSE_EVENTS__TERM_= TYPE_OVERWRITE); } no-overwrite { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_NOOVERWRITE= ); } percore { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); } aux-output { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); } +aux-pause { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_PAUSE); } +aux-resume { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_RESUME); } +aux-start-paused { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_STAR= T_PAUSED); } aux-sample-size { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMP= LE_SIZE); } metric-id { return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); } cpu-cycles|cycles { return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES)= ; } diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/pe= rf_event_attr_fprintf.c index 8f04d3b7f3ec..e6ba0ac73182 100644 --- a/tools/perf/util/perf_event_attr_fprintf.c +++ b/tools/perf/util/perf_event_attr_fprintf.c @@ -309,6 +309,7 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_even= t_attr *attr, PRINT_ATTRf(inherit_thread, p_unsigned); PRINT_ATTRf(remove_on_exec, p_unsigned); PRINT_ATTRf(sigtrap, p_unsigned); + PRINT_ATTRf(aux_start_paused, p_unsigned); =20 PRINT_ATTRn("{ wakeup_events, wakeup_watermark }", wakeup_events, p_unsig= ned, false); PRINT_ATTRf(bp_type, p_unsigned); @@ -323,6 +324,8 @@ int perf_event_attr__fprintf(FILE *fp, struct perf_even= t_attr *attr, PRINT_ATTRf(sample_max_stack, p_unsigned); PRINT_ATTRf(aux_sample_size, p_unsigned); PRINT_ATTRf(sig_data, p_unsigned); + PRINT_ATTRf(aux_pause, p_unsigned); + PRINT_ATTRf(aux_resume, p_unsigned); =20 return ret; } --=20 2.34.1