From nobody Thu Nov 28 15:53:39 2024 Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 0EA56188938; Tue, 1 Oct 2024 12:15:45 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=217.140.110.172 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1727784948; cv=none; b=UfwEExSt3MKbWe2ojGrA4K5InnNHIqTa7n2byNtRPCxSi0D/baCTATxB96S6wokQAUHRLdrKAP+KKUIZivNx/amx1AZCsOpxRvq+ZFZJKC6XvUt6aTp53aLr/L7LORdenzcJFo+X17N06+aIJLaTreHKS1xSYPllOTpR1T7lZGg= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1727784948; c=relaxed/simple; bh=HwDLj/H7orJxKlxbKhY5waYIeG+1lBz6C9eK5XxG0Yg=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=roFOyndBBPKhlGRXKthUZECsX7YKVMUdxlq/11gajbqMNbxrl0sjAgbBt8Oo6cs4jbkIs51GLbxeYIaev6ctXZpkhxp7+4ZHjRIuM/C/IywqNNGuGMtcOXX2ktZr5ABVX69z07JLBm8Zhh8Q/MMNWczdD6+WYd2No/cp431tfmQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com; spf=pass smtp.mailfrom=arm.com; arc=none smtp.client-ip=217.140.110.172 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=arm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=arm.com 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 B98E0367; Tue, 1 Oct 2024 05:16:14 -0700 (PDT) Received: from e126817.cambridge.arm.com (e126817.cambridge.arm.com [10.2.3.5]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 3961B3F58B; Tue, 1 Oct 2024 05:15:43 -0700 (PDT) From: Ben Gainey To: peterz@infradead.org, mingo@redhat.com, acme@kernel.org, namhyung@kernel.org Cc: james.clark@arm.com, mark.rutland@arm.com, alexander.shishkin@linux.intel.com, jolsa@kernel.org, irogers@google.com, adrian.hunter@intel.com, linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org, Ben Gainey Subject: [PATCH v12 1/2] tools/perf: Correctly calculate sample period for inherited SAMPLE_READ values Date: Tue, 1 Oct 2024 13:15:04 +0100 Message-ID: <20241001121505.1009685-2-ben.gainey@arm.com> X-Mailer: git-send-email 2.46.1 In-Reply-To: <20241001121505.1009685-1-ben.gainey@arm.com> References: <20241001121505.1009685-1-ben.gainey@arm.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" Sample period calculation in deliver_sample_value is updated to calculate the per-thread period delta for events that are inherit + PERF_SAMPLE_READ. When the sampling event has this configuration, the read_format.id is used with the tid from the sample to lookup the storage of the previously accumulated counter total before calculating the delta. All existing valid configurations where read_format.value represents some global value continue to use just the read_format.id to locate the storage of the previously accumulated total. perf_sample_id is modified to support tracking per-thread values, along with the existing global per-id values. In the per-thread case, values are stored in a hash by tid within the perf_sample_id, and are dynamically allocated as the number is not known ahead of time. Signed-off-by: Ben Gainey --- tools/lib/perf/evsel.c | 48 +++++++++++++++++++ tools/lib/perf/include/internal/evsel.h | 63 ++++++++++++++++++++++++- tools/perf/util/session.c | 28 +++++++---- 3 files changed, 128 insertions(+), 11 deletions(-) diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c index c07160953224..c475319e2e41 100644 --- a/tools/lib/perf/evsel.c +++ b/tools/lib/perf/evsel.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -23,6 +24,7 @@ void perf_evsel__init(struct perf_evsel *evsel, struct pe= rf_event_attr *attr, int idx) { INIT_LIST_HEAD(&evsel->node); + INIT_LIST_HEAD(&evsel->per_stream_periods); evsel->attr =3D *attr; evsel->idx =3D idx; evsel->leader =3D evsel; @@ -531,10 +533,56 @@ int perf_evsel__alloc_id(struct perf_evsel *evsel, in= t ncpus, int nthreads) =20 void perf_evsel__free_id(struct perf_evsel *evsel) { + struct perf_sample_id_period *pos, *n; + xyarray__delete(evsel->sample_id); evsel->sample_id =3D NULL; zfree(&evsel->id); evsel->ids =3D 0; + + perf_evsel_for_each_per_thread_period_safe(evsel, n, pos) { + list_del_init(&pos->node); + free(pos); + } +} + +bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evse= l) +{ + return (evsel->attr.sample_type & PERF_SAMPLE_READ) && + (evsel->attr.sample_type & PERF_SAMPLE_TID) && + evsel->attr.inherit; +} + +u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 ti= d, bool per_thread) +{ + struct hlist_head *head; + struct perf_sample_id_period *res; + int hash; + + if (!per_thread) + return &sid->period; + + hash =3D hash_32(tid, PERF_SAMPLE_ID__HLIST_BITS); + head =3D &sid->periods[hash]; + + hlist_for_each_entry(res, head, hnode) + if (res->tid =3D=3D tid) + return &res->period; + + if (sid->evsel =3D=3D NULL) + return NULL; + + res =3D zalloc(sizeof(struct perf_sample_id_period)); + if (res =3D=3D NULL) + return NULL; + + INIT_LIST_HEAD(&res->node); + res->tid =3D tid; + + list_add_tail(&res->node, &sid->evsel->per_stream_periods); + hlist_add_head(&res->hnode, &sid->periods[hash]); + + return &res->period; } =20 void perf_counts_values__scale(struct perf_counts_values *count, diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/inclu= de/internal/evsel.h index 5cd220a61962..ea78defa77d0 100644 --- a/tools/lib/perf/include/internal/evsel.h +++ b/tools/lib/perf/include/internal/evsel.h @@ -11,6 +11,32 @@ struct perf_thread_map; struct xyarray; =20 +/** + * The per-thread accumulated period storage node. + */ +struct perf_sample_id_period { + struct list_head node; + struct hlist_node hnode; + /* Holds total ID period value for PERF_SAMPLE_READ processing. */ + u64 period; + /* The TID that the values belongs to */ + u32 tid; +}; + +/** + * perf_evsel_for_each_per_thread_period_safe - safely iterate thru all the + * per_stream_periods + * @evlist:perf_evsel instance to iterate + * @item: struct perf_sample_id_period iterator + * @tmp: struct perf_sample_id_period temp iterator + */ +#define perf_evsel_for_each_per_thread_period_safe(evsel, tmp, item) \ + list_for_each_entry_safe(item, tmp, &(evsel)->per_stream_periods, node) + + +#define PERF_SAMPLE_ID__HLIST_BITS 4 +#define PERF_SAMPLE_ID__HLIST_SIZE (1 << PERF_SAMPLE_ID__HLIST_BITS) + /* * Per fd, to map back from PERF_SAMPLE_ID to evsel, only used when there = are * more than one entry in the evlist. @@ -34,8 +60,32 @@ struct perf_sample_id { pid_t machine_pid; struct perf_cpu vcpu; =20 - /* Holds total ID period value for PERF_SAMPLE_READ processing. */ - u64 period; + /* + * Per-thread, and global event counts are mutually exclusive: + * Whilst it is possible to combine events into a group with differing + * values of PERF_SAMPLE_READ, it is not valid to have inconsistent + * values for `inherit`. Therefore it is not possible to have a + * situation where a per-thread event is sampled as a global event; + * all !inherit groups are global, and all groups where the sampling + * event is inherit + PERF_SAMPLE_READ will be per-thread. Any event + * that is part of such a group that is inherit but not PERF_SAMPLE_READ + * will be read as per-thread. If such an event can also trigger a + * sample (such as with sample_period > 0) then it will not cause + * `read_format` to be included in its PERF_RECORD_SAMPLE, and + * therefore will not expose the per-thread group members as global. + */ + union { + /* + * Holds total ID period value for PERF_SAMPLE_READ processing + * (when period is not per-thread). + */ + u64 period; + /* + * Holds total ID period value for PERF_SAMPLE_READ processing + * (when period is per-thread). + */ + struct hlist_head periods[PERF_SAMPLE_ID__HLIST_SIZE]; + }; }; =20 struct perf_evsel { @@ -58,6 +108,10 @@ struct perf_evsel { u32 ids; struct perf_evsel *leader; =20 + /* For events where the read_format value is per-thread rather than + * global, stores the per-thread cumulative period */ + struct list_head per_stream_periods; + /* parse modifier helper */ int nr_members; /* @@ -88,4 +142,9 @@ int perf_evsel__apply_filter(struct perf_evsel *evsel, c= onst char *filter); int perf_evsel__alloc_id(struct perf_evsel *evsel, int ncpus, int nthreads= ); void perf_evsel__free_id(struct perf_evsel *evsel); =20 +bool perf_evsel__attr_has_per_thread_sample_period(struct perf_evsel *evse= l); + +u64 *perf_sample_id__get_period_storage(struct perf_sample_id *sid, u32 ti= d, + bool per_thread); + #endif /* __LIBPERF_INTERNAL_EVSEL_H */ diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index dbaf07bf6c5f..507e6cba9545 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1171,18 +1171,24 @@ static int deliver_sample_value(struct evlist *evli= st, union perf_event *event, struct perf_sample *sample, struct sample_read_value *v, - struct machine *machine) + struct machine *machine, + bool per_thread) { struct perf_sample_id *sid =3D evlist__id2sid(evlist, v->id); struct evsel *evsel; + u64 *storage =3D NULL; =20 if (sid) { + storage =3D perf_sample_id__get_period_storage(sid, sample->tid, per_thr= ead); + } + + if (storage) { sample->id =3D v->id; - sample->period =3D v->value - sid->period; - sid->period =3D v->value; + sample->period =3D v->value - *storage; + *storage =3D v->value; } =20 - if (!sid || sid->evsel =3D=3D NULL) { + if (!storage || sid->evsel =3D=3D NULL) { ++evlist->stats.nr_unknown_id; return 0; } @@ -1203,17 +1209,19 @@ static int deliver_sample_group(struct evlist *evli= st, union perf_event *event, struct perf_sample *sample, struct machine *machine, - u64 read_format) + u64 read_format, + bool per_thread) { int ret =3D -EINVAL; struct sample_read_value *v =3D sample->read.group.values; =20 if (tool->dont_split_sample_group) - return deliver_sample_value(evlist, tool, event, sample, v, machine); + return deliver_sample_value(evlist, tool, event, sample, v, machine, + per_thread); =20 sample_read_group__for_each(v, sample->read.group.nr, read_format) { ret =3D deliver_sample_value(evlist, tool, event, sample, v, - machine); + machine, per_thread); if (ret) break; } @@ -1228,6 +1236,7 @@ static int evlist__deliver_sample(struct evlist *evli= st, const struct perf_tool /* We know evsel !=3D NULL. */ u64 sample_type =3D evsel->core.attr.sample_type; u64 read_format =3D evsel->core.attr.read_format; + bool per_thread =3D perf_evsel__attr_has_per_thread_sample_period(&evsel-= >core); =20 /* Standard sample delivery. */ if (!(sample_type & PERF_SAMPLE_READ)) @@ -1236,10 +1245,11 @@ static int evlist__deliver_sample(struct evlist *ev= list, const struct perf_tool /* For PERF_SAMPLE_READ we have either single or group mode. */ if (read_format & PERF_FORMAT_GROUP) return deliver_sample_group(evlist, tool, event, sample, - machine, read_format); + machine, read_format, per_thread); else return deliver_sample_value(evlist, tool, event, sample, - &sample->read.one, machine); + &sample->read.one, machine, + per_thread); } =20 static int machines__deliver_event(struct machines *machines, --=20 2.46.1