From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 0287325A627; Tue, 27 May 2025 17:47:03 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748368024; cv=none; b=iKf0ClV7BRe50CnksK8zGPtJdJ6ehYBllrAmnfJxdp6eCc9ExOl98o/+7rlnmlMo77DNec2DghX5q2tbE+F/bJiHCtFS0WS8dD1qRqsNkn/dikVWhWEFtLfp2g4CsahMHepnJX1gYWBkGAhEkMa3zKQQtkZdwrriU/JF9RkAvJE= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1748368024; c=relaxed/simple; bh=MDjeEsSvK8JQMVNt6WEw4Nf6onEnDl3AdR5lJQtibqE=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=t4rdMS7sEyw6GopGcTgPJfM2aVaSn0v/ItEP8f6/7np3Ed8pSmNO1gt5451+IIVL3YEWPKvjk/gvusF0hOOquDu80Ip1AGjtUGtUcZO0qaLfyqo2OZ4gX2/LVJ0oQPZApIeXn4rUSqiEipM3tfpIO/D+QkHWMIzI+lYVH+KsuH8= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b=OQEucnIe; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b="OQEucnIe" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 76B73C4CEE9; Tue, 27 May 2025 17:47:03 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1748368023; bh=MDjeEsSvK8JQMVNt6WEw4Nf6onEnDl3AdR5lJQtibqE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=OQEucnIe+YXbNnPs9utm4F5M5ul70zIJrN26qv7N7bSEjgpYdFq3QL8XIOBJrtQ4v IocTYgLATU8tWfZsgh7rpYaTX7HPYMQDu5UWP+CAJasTLWwMG2/pi7fb5n757haiF6 mKr7x8AcfPcxP9mniug+oS+X2vZ3Pcvl6i+QSW7k= From: Greg Kroah-Hartman To: stable@vger.kernel.org Cc: Greg Kroah-Hartman , patches@lists.linux.dev, "Peter Zijlstra (Intel)" , Kan Liang , Sasha Levin Subject: [PATCH 6.14 573/783] perf: Avoid the read if the count is already updated Date: Tue, 27 May 2025 18:26:10 +0200 Message-ID: <20250527162536.484103665@linuxfoundation.org> X-Mailer: git-send-email 2.49.0 In-Reply-To: <20250527162513.035720581@linuxfoundation.org> References: <20250527162513.035720581@linuxfoundation.org> User-Agent: quilt/0.68 X-stable: review X-Patchwork-Hint: ignore Precedence: bulk X-Mailing-List: patches@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit 6.14-stable review patch. If anyone has any objections, please let me know. ------------------ From: Peter Zijlstra (Intel) [ Upstream commit 8ce939a0fa194939cc1f92dbd8bc1a7806e7d40a ] The event may have been updated in the PMU-specific implementation, e.g., Intel PEBS counters snapshotting. The common code should not read and overwrite the value. The PERF_SAMPLE_READ in the data->sample_type can be used to detect whether the PMU-specific value is available. If yes, avoid the pmu->read() in the common code. Add a new flag, skip_read, to track the case. Factor out a perf_pmu_read() to clean up the code. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20250121152303.3128733-3-kan.liang@linux.intel.com Signed-off-by: Sasha Levin --- include/linux/perf_event.h | 8 +++++++- kernel/events/core.c | 33 ++++++++++++++++----------------- kernel/events/ring_buffer.c | 1 + 3 files changed, 24 insertions(+), 18 deletions(-) diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 93ea9c6672f0e..3d5814c6d251c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1098,7 +1098,13 @@ struct perf_output_handle { struct perf_buffer *rb; unsigned long wakeup; unsigned long size; - u64 aux_flags; + union { + u64 flags; /* perf_output*() */ + u64 aux_flags; /* perf_aux_output*() */ + struct { + u64 skip_read : 1; + }; + }; union { void *addr; unsigned long head; diff --git a/kernel/events/core.c b/kernel/events/core.c index dda1670b3539a..6fa70b3826d0e 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -1191,6 +1191,12 @@ static void perf_assert_pmu_disabled(struct pmu *pmu) WARN_ON_ONCE(*this_cpu_ptr(pmu->pmu_disable_count) == 0); } +static inline void perf_pmu_read(struct perf_event *event) +{ + if (event->state == PERF_EVENT_STATE_ACTIVE) + event->pmu->read(event); +} + static void get_ctx(struct perf_event_context *ctx) { refcount_inc(&ctx->refcount); @@ -3478,8 +3484,7 @@ static void __perf_event_sync_stat(struct perf_event *event, * we know the event must be on the current CPU, therefore we * don't need to use it. */ - if (event->state == PERF_EVENT_STATE_ACTIVE) - event->pmu->read(event); + perf_pmu_read(event); perf_event_update_time(event); @@ -4625,15 +4630,8 @@ static void __perf_event_read(void *info) pmu->read(event); - for_each_sibling_event(sub, event) { - if (sub->state == PERF_EVENT_STATE_ACTIVE) { - /* - * Use sibling's PMU rather than @event's since - * sibling could be on different (eg: software) PMU. - */ - sub->pmu->read(sub); - } - } + for_each_sibling_event(sub, event) + perf_pmu_read(sub); data->ret = pmu->commit_txn(pmu); @@ -7451,9 +7449,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) values[n++] = running; - if ((leader != event) && - (leader->state == PERF_EVENT_STATE_ACTIVE)) - leader->pmu->read(leader); + if ((leader != event) && !handle->skip_read) + perf_pmu_read(leader); values[n++] = perf_event_count(leader, self); if (read_format & PERF_FORMAT_ID) @@ -7466,9 +7463,8 @@ static void perf_output_read_group(struct perf_output_handle *handle, for_each_sibling_event(sub, leader) { n = 0; - if ((sub != event) && - (sub->state == PERF_EVENT_STATE_ACTIVE)) - sub->pmu->read(sub); + if ((sub != event) && !handle->skip_read) + perf_pmu_read(sub); values[n++] = perf_event_count(sub, self); if (read_format & PERF_FORMAT_ID) @@ -7527,6 +7523,9 @@ void perf_output_sample(struct perf_output_handle *handle, { u64 sample_type = data->type; + if (data->sample_flags & PERF_SAMPLE_READ) + handle->skip_read = 1; + perf_output_put(handle, *header); if (sample_type & PERF_SAMPLE_IDENTIFIER) diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c index 09459647cb822..5130b119d0ae0 100644 --- a/kernel/events/ring_buffer.c +++ b/kernel/events/ring_buffer.c @@ -185,6 +185,7 @@ __perf_output_begin(struct perf_output_handle *handle, handle->rb = rb; handle->event = event; + handle->flags = 0; have_lost = local_read(&rb->lost); if (unlikely(have_lost)) { -- 2.39.5