From patchwork Mon Jul 26 14:46:48 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 485908 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=-15.7 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, 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 9147FC4338F for ; Mon, 26 Jul 2021 14:42:47 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 7887B60F58 for ; Mon, 26 Jul 2021 14:42:47 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S233206AbhGZOCR (ORCPT ); Mon, 26 Jul 2021 10:02:17 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:60526 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234614AbhGZOCR (ORCPT ); Mon, 26 Jul 2021 10:02:17 -0400 Received: from mail-pl1-x630.google.com (mail-pl1-x630.google.com [IPv6:2607:f8b0:4864:20::630]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id CBC24C061757; Mon, 26 Jul 2021 07:42:45 -0700 (PDT) Received: by mail-pl1-x630.google.com with SMTP id e14so11898590plh.8; Mon, 26 Jul 2021 07:42:45 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=7QcrlTywukSz2PKz24z0zEJ3rCmK55/THXy/9fxZEN8=; b=N5DLQKs95Ra/6WhIDTJWzfdamAUA+HGnDFaHuBwvGw7F6ngrcPWy5fBhiXxAow3djk fNYIhEo5LZj6fKAGbl69yUUseFiBFMeKzctq9fwht6IBkLExso4mdoKH0gmLw6ixZfIg wa5WXjGycPtRxuajpToyMQgz6m29HOZ69j0ffST1ZiLA6kvYGAge0PmY4hufVxWTFwaJ fxv3Q9tt0mcaQSIUAqD8X8FH1EcbeyhDC4XxiI+zWpPIWmIVC4ctLVNuM5KvLA4lJkUl rdLsSf98LJIwKtkU7quIW+TSOvjZyCfOO8E0H7TUgCEnT3A7vknyHmtsixMJiPteyo/g ptyA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=7QcrlTywukSz2PKz24z0zEJ3rCmK55/THXy/9fxZEN8=; b=eN1mPHVsOc2+W0hqn3pJViCLbTk8gAYv2L+s8RKEqS8NXTpOhAtdWdvQX2AVQOSUKK kcRtqyIeZ77H7QMCLzwKneXUi3/8QfveFZIw5weLKFqGd3bhx940/hxzGdW7ut4sOpjf we5eQa+6QibD+hMa9e0K76k5+9MaXPrzpJsnqTOJjdkEOJYfSKJ+gsqSkBHWrcPYDONh MHDZyOc4j6V5t7rANWg+CJil31mzW9r214BzV2e5CN63POWjhIqKH9K1aDtXrIPVlTHp N02/MXymi8AaeQTPEisBj9MSgLSC2TPxsYEQX8nuV7+ivPHEjspLEfZ+kHnFvqxlt7QD rFDw== X-Gm-Message-State: AOAM532m500qQ6gcuacR0FzIg09w/YWR89wh1pN9LD8Cz6cesprPuTcI NvIIbp4ScTZOwyXgZTfxfII= X-Google-Smtp-Source: ABdhPJzeAdVynpqWMkO33MeI9BK8+7aHKZ25qaK5ssVs90hsKP33OvBBbWf83/PLhU7UO8TCc6/jDQ== X-Received: by 2002:a17:902:74c9:b029:12b:60fa:bde0 with SMTP id f9-20020a17090274c9b029012b60fabde0mr14808293plt.8.1627310565295; Mon, 26 Jul 2021 07:42:45 -0700 (PDT) Received: from localhost ([2601:1c0:5200:a6:307:a401:7b76:c6e5]) by smtp.gmail.com with ESMTPSA id g12sm202316pfv.167.2021.07.26.07.42.43 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 26 Jul 2021 07:42:44 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: Rob Clark , Rob Clark , Sean Paul , David Airlie , Daniel Vetter , Jordan Crouse , Jonathan Marek , Akhil P Oommen , Sai Prakash Ranjan , Sharat Masetty , Douglas Anderson , linux-kernel@vger.kernel.org (open list), linux-arm-msm@vger.kernel.org (open list:DRM DRIVER FOR MSM ADRENO GPU), freedreno@lists.freedesktop.org (open list:DRM DRIVER FOR MSM ADRENO GPU) Subject: [PATCH v2 1/3] drm/msm: Split out devfreq handling Date: Mon, 26 Jul 2021 07:46:48 -0700 Message-Id: <20210726144653.2180096-2-robdclark@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210726144653.2180096-1-robdclark@gmail.com> References: <20210726144653.2180096-1-robdclark@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-arm-msm@vger.kernel.org From: Rob Clark Before we start adding more cleverness, split it into it's own file. Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov --- drivers/gpu/drm/msm/Makefile | 1 + drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 4 +- drivers/gpu/drm/msm/msm_gpu.c | 116 +--------------------- drivers/gpu/drm/msm/msm_gpu.h | 32 +++++-- drivers/gpu/drm/msm/msm_gpu_devfreq.c | 133 ++++++++++++++++++++++++++ 5 files changed, 165 insertions(+), 121 deletions(-) create mode 100644 drivers/gpu/drm/msm/msm_gpu_devfreq.c diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile index 2c00aa70b708..904535eda0c4 100644 --- a/drivers/gpu/drm/msm/Makefile +++ b/drivers/gpu/drm/msm/Makefile @@ -90,6 +90,7 @@ msm-y := \ msm_gem_submit.o \ msm_gem_vma.o \ msm_gpu.o \ + msm_gpu_devfreq.o \ msm_iommu.o \ msm_perf.o \ msm_rd.o \ diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 9db9f7847ea8..91f637b908f4 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1477,7 +1477,7 @@ static int a6xx_pm_resume(struct msm_gpu *gpu) if (ret) return ret; - msm_gpu_resume_devfreq(gpu); + msm_devfreq_resume(gpu); a6xx_llc_activate(a6xx_gpu); @@ -1494,7 +1494,7 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) a6xx_llc_deactivate(a6xx_gpu); - devfreq_suspend_device(gpu->devfreq.devfreq); + msm_devfreq_suspend(gpu); ret = a6xx_gmu_stop(a6xx_gpu); if (ret) diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 647af45cf892..fedbd785e42f 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -13,8 +13,6 @@ #include #include -#include -#include #include #include @@ -22,106 +20,6 @@ * Power Management: */ -static int msm_devfreq_target(struct device *dev, unsigned long *freq, - u32 flags) -{ - struct msm_gpu *gpu = dev_to_gpu(dev); - struct dev_pm_opp *opp; - - opp = devfreq_recommended_opp(dev, freq, flags); - - if (IS_ERR(opp)) - return PTR_ERR(opp); - - trace_msm_gpu_freq_change(dev_pm_opp_get_freq(opp)); - - if (gpu->funcs->gpu_set_freq) - gpu->funcs->gpu_set_freq(gpu, opp); - else - clk_set_rate(gpu->core_clk, *freq); - - dev_pm_opp_put(opp); - - return 0; -} - -static int msm_devfreq_get_dev_status(struct device *dev, - struct devfreq_dev_status *status) -{ - struct msm_gpu *gpu = dev_to_gpu(dev); - ktime_t time; - - if (gpu->funcs->gpu_get_freq) - status->current_frequency = gpu->funcs->gpu_get_freq(gpu); - else - status->current_frequency = clk_get_rate(gpu->core_clk); - - status->busy_time = gpu->funcs->gpu_busy(gpu); - - time = ktime_get(); - status->total_time = ktime_us_delta(time, gpu->devfreq.time); - gpu->devfreq.time = time; - - return 0; -} - -static int msm_devfreq_get_cur_freq(struct device *dev, unsigned long *freq) -{ - struct msm_gpu *gpu = dev_to_gpu(dev); - - if (gpu->funcs->gpu_get_freq) - *freq = gpu->funcs->gpu_get_freq(gpu); - else - *freq = clk_get_rate(gpu->core_clk); - - return 0; -} - -static struct devfreq_dev_profile msm_devfreq_profile = { - .polling_ms = 10, - .target = msm_devfreq_target, - .get_dev_status = msm_devfreq_get_dev_status, - .get_cur_freq = msm_devfreq_get_cur_freq, -}; - -static void msm_devfreq_init(struct msm_gpu *gpu) -{ - /* We need target support to do devfreq */ - if (!gpu->funcs->gpu_busy) - return; - - msm_devfreq_profile.initial_freq = gpu->fast_rate; - - /* - * Don't set the freq_table or max_state and let devfreq build the table - * from OPP - * After a deferred probe, these may have be left to non-zero values, - * so set them back to zero before creating the devfreq device - */ - msm_devfreq_profile.freq_table = NULL; - msm_devfreq_profile.max_state = 0; - - gpu->devfreq.devfreq = devm_devfreq_add_device(&gpu->pdev->dev, - &msm_devfreq_profile, DEVFREQ_GOV_SIMPLE_ONDEMAND, - NULL); - - if (IS_ERR(gpu->devfreq.devfreq)) { - DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n"); - gpu->devfreq.devfreq = NULL; - return; - } - - devfreq_suspend_device(gpu->devfreq.devfreq); - - gpu->cooling = of_devfreq_cooling_register(gpu->pdev->dev.of_node, - gpu->devfreq.devfreq); - if (IS_ERR(gpu->cooling)) { - DRM_DEV_ERROR(&gpu->pdev->dev, - "Couldn't register GPU cooling device\n"); - gpu->cooling = NULL; - } -} - static int enable_pwrrail(struct msm_gpu *gpu) { struct drm_device *dev = gpu->dev; @@ -196,14 +94,6 @@ static int disable_axi(struct msm_gpu *gpu) return 0; } -void msm_gpu_resume_devfreq(struct msm_gpu *gpu) -{ - gpu->devfreq.busy_cycles = 0; - gpu->devfreq.time = ktime_get(); - - devfreq_resume_device(gpu->devfreq.devfreq); -} - int msm_gpu_pm_resume(struct msm_gpu *gpu) { int ret; @@ -223,7 +113,7 @@ int msm_gpu_pm_resume(struct msm_gpu *gpu) if (ret) return ret; - msm_gpu_resume_devfreq(gpu); + msm_devfreq_resume(gpu); gpu->needs_hw_init = true; @@ -237,7 +127,7 @@ int msm_gpu_pm_suspend(struct msm_gpu *gpu) DBG("%s", gpu->name); trace_msm_gpu_suspend(0); - devfreq_suspend_device(gpu->devfreq.devfreq); + msm_devfreq_suspend(gpu); ret = disable_axi(gpu); if (ret) @@ -1116,5 +1006,5 @@ void msm_gpu_cleanup(struct msm_gpu *gpu) kthread_destroy_worker(gpu->worker); } - devfreq_cooling_unregister(gpu->cooling); + msm_devfreq_cleanup(gpu); } diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index ef41ec09f59c..2e61d05293e6 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -80,6 +80,26 @@ struct msm_gpu_fault_info { const char *block; }; +/** + * struct msm_gpu_devfreq - devfreq related state + */ +struct msm_gpu_devfreq { + /** devfreq: devfreq instance */ + struct devfreq *devfreq; + + /** + * busy_cycles: + * + * Used by implementation of gpu->gpu_busy() to track the last + * busy counter value, for calculating elapsed busy cycles since + * last sampling period. + */ + u64 busy_cycles; + + /** time: Time of last sampling period. */ + ktime_t time; +}; + struct msm_gpu { const char *name; struct drm_device *dev; @@ -151,11 +171,7 @@ struct msm_gpu { struct drm_gem_object *memptrs_bo; - struct { - struct devfreq *devfreq; - u64 busy_cycles; - ktime_t time; - } devfreq; + struct msm_gpu_devfreq devfreq; uint32_t suspend_count; @@ -301,7 +317,11 @@ static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val) int msm_gpu_pm_suspend(struct msm_gpu *gpu); int msm_gpu_pm_resume(struct msm_gpu *gpu); -void msm_gpu_resume_devfreq(struct msm_gpu *gpu); + +void msm_devfreq_init(struct msm_gpu *gpu); +void msm_devfreq_cleanup(struct msm_gpu *gpu); +void msm_devfreq_resume(struct msm_gpu *gpu); +void msm_devfreq_suspend(struct msm_gpu *gpu); int msm_gpu_hw_init(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c new file mode 100644 index 000000000000..3bcea0baddab --- /dev/null +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2013 Red Hat + * Author: Rob Clark + */ + +#include "msm_gpu.h" +#include "msm_gpu_trace.h" + +#include +#include + +/* + * Power Management: + */ + +static int msm_devfreq_target(struct device *dev, unsigned long *freq, + u32 flags) +{ + struct msm_gpu *gpu = dev_to_gpu(dev); + struct dev_pm_opp *opp; + + opp = devfreq_recommended_opp(dev, freq, flags); + + if (IS_ERR(opp)) + return PTR_ERR(opp); + + trace_msm_gpu_freq_change(dev_pm_opp_get_freq(opp)); + + if (gpu->funcs->gpu_set_freq) + gpu->funcs->gpu_set_freq(gpu, opp); + else + clk_set_rate(gpu->core_clk, *freq); + + dev_pm_opp_put(opp); + + return 0; +} + +static int msm_devfreq_get_dev_status(struct device *dev, + struct devfreq_dev_status *status) +{ + struct msm_gpu *gpu = dev_to_gpu(dev); + ktime_t time; + + if (gpu->funcs->gpu_get_freq) + status->current_frequency = gpu->funcs->gpu_get_freq(gpu); + else + status->current_frequency = clk_get_rate(gpu->core_clk); + + status->busy_time = gpu->funcs->gpu_busy(gpu); + + time = ktime_get(); + status->total_time = ktime_us_delta(time, gpu->devfreq.time); + gpu->devfreq.time = time; + + return 0; +} + +static int msm_devfreq_get_cur_freq(struct device *dev, unsigned long *freq) +{ + struct msm_gpu *gpu = dev_to_gpu(dev); + + if (gpu->funcs->gpu_get_freq) + *freq = gpu->funcs->gpu_get_freq(gpu); + else + *freq = clk_get_rate(gpu->core_clk); + + return 0; +} + +static struct devfreq_dev_profile msm_devfreq_profile = { + .polling_ms = 10, + .target = msm_devfreq_target, + .get_dev_status = msm_devfreq_get_dev_status, + .get_cur_freq = msm_devfreq_get_cur_freq, +}; + +void msm_devfreq_init(struct msm_gpu *gpu) +{ + /* We need target support to do devfreq */ + if (!gpu->funcs->gpu_busy) + return; + + msm_devfreq_profile.initial_freq = gpu->fast_rate; + + /* + * Don't set the freq_table or max_state and let devfreq build the table + * from OPP + * After a deferred probe, these may have be left to non-zero values, + * so set them back to zero before creating the devfreq device + */ + msm_devfreq_profile.freq_table = NULL; + msm_devfreq_profile.max_state = 0; + + gpu->devfreq.devfreq = devm_devfreq_add_device(&gpu->pdev->dev, + &msm_devfreq_profile, DEVFREQ_GOV_SIMPLE_ONDEMAND, + NULL); + + if (IS_ERR(gpu->devfreq.devfreq)) { + DRM_DEV_ERROR(&gpu->pdev->dev, "Couldn't initialize GPU devfreq\n"); + gpu->devfreq.devfreq = NULL; + return; + } + + devfreq_suspend_device(gpu->devfreq.devfreq); + + gpu->cooling = of_devfreq_cooling_register(gpu->pdev->dev.of_node, + gpu->devfreq.devfreq); + if (IS_ERR(gpu->cooling)) { + DRM_DEV_ERROR(&gpu->pdev->dev, + "Couldn't register GPU cooling device\n"); + gpu->cooling = NULL; + } +} + +void msm_devfreq_cleanup(struct msm_gpu *gpu) +{ + devfreq_cooling_unregister(gpu->cooling); +} + +void msm_devfreq_resume(struct msm_gpu *gpu) +{ + gpu->devfreq.busy_cycles = 0; + gpu->devfreq.time = ktime_get(); + + devfreq_resume_device(gpu->devfreq.devfreq); +} + +void msm_devfreq_suspend(struct msm_gpu *gpu) +{ + devfreq_suspend_device(gpu->devfreq.devfreq); +} From patchwork Mon Jul 26 14:46:49 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 486850 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=-15.7 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, 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 D9CC2C4338F for ; Mon, 26 Jul 2021 14:42:50 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id C4ED760F5C for ; Mon, 26 Jul 2021 14:42:50 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234679AbhGZOCV (ORCPT ); Mon, 26 Jul 2021 10:02:21 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:60536 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234614AbhGZOCU (ORCPT ); Mon, 26 Jul 2021 10:02:20 -0400 Received: from mail-pl1-x630.google.com (mail-pl1-x630.google.com [IPv6:2607:f8b0:4864:20::630]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id E6B73C061757; Mon, 26 Jul 2021 07:42:47 -0700 (PDT) Received: by mail-pl1-x630.google.com with SMTP id c11so11803055plg.11; Mon, 26 Jul 2021 07:42:47 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=8PbuIDLJSwDZoHRmQDtVVH8v7wrAjGN8POl6WAu5zOM=; b=ChcDtB/kxIXXTedMqyBkWFdJKgGXHSEEl8e4hMFgzXaG8W/+JMBOe1VRI4uF1NqLTj KJcBuItjYQpAyJJEfLrbcpvWnGGS5fi/VGaJxZmoHep0+sRvdoJ/vkTjKguE3XVrSahx Xo0Fqk7oPC0SrD1NhWtr84MByOX4i0IVEr7g2R7QtV1eEmlCAETKkniiAZovTp6NAW0R s2+dwCwAKu4Ie+QMCTgEb6hIPgU6BiQPeOhZGzWRb4l4lHqm8XEimQ8alzJVLs4SASJj E0GFAr3LSFtc5axCNmsm5mWUx1ViBi1C5/6oFsd6X+UWeAlv0nwppbUc+bMnINZ0TUnf 7Qlg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=8PbuIDLJSwDZoHRmQDtVVH8v7wrAjGN8POl6WAu5zOM=; b=amDsE/1ZbfVS3ZgpdfWKbEKJisncQYlHwjklb7xpQnRaM2iu1+UY1m0miz+Zh8smNG OYqJj3hXZOEbwaXkjBkkBEG9QIrpkvXsoAxV8WCNTASCwb+UMkLgjIUHkQNkBhafQmUD eUurLo1Ilufh+jsiXApMG+lEtuZJhXOPKHSJKJpo+d0UNVFeEsKw9jRO3DTOOkuLf9Nc XhcakkVsYeMOO9XA2INXKOC22QPZyWMSzshYPzDgyKnzpeYN2T3U2e9XR3of6pGUCrQ3 C2WCE8y49NOCKBGgxybZJ8wpycO7rTt2Ztb3UG2U/28IaE/77yXUS2TvaskTUEY/HEIJ Urdg== X-Gm-Message-State: AOAM530x4koytcTwmopsipzJ8r5/DW1QAWM8LKUj+aBQS22tVKODMu6H H5R6Vs4OjmiOnzk6osoD7XE= X-Google-Smtp-Source: ABdhPJz3zGdCxKIjdfgjhyaQKwvGv8VTrN2JA1XMA101kxTKicOrL4ZtEl4oonTOj8Kw7kbTic+20g== X-Received: by 2002:a65:684d:: with SMTP id q13mr18358200pgt.24.1627310567478; Mon, 26 Jul 2021 07:42:47 -0700 (PDT) Received: from localhost ([2601:1c0:5200:a6:307:a401:7b76:c6e5]) by smtp.gmail.com with ESMTPSA id r13sm3626970pgi.78.2021.07.26.07.42.46 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 26 Jul 2021 07:42:46 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: Rob Clark , Rob Clark , Sean Paul , David Airlie , Daniel Vetter , linux-arm-msm@vger.kernel.org (open list:DRM DRIVER FOR MSM ADRENO GPU), freedreno@lists.freedesktop.org (open list:DRM DRIVER FOR MSM ADRENO GPU), linux-kernel@vger.kernel.org (open list) Subject: [PATCH v2 2/3] drm/msm: Split out get_freq() helper Date: Mon, 26 Jul 2021 07:46:49 -0700 Message-Id: <20210726144653.2180096-3-robdclark@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210726144653.2180096-1-robdclark@gmail.com> References: <20210726144653.2180096-1-robdclark@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-arm-msm@vger.kernel.org From: Rob Clark In the next patch, it grows a bit more, so lets not duplicate the logic in multiple places. Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_gpu_devfreq.c | 21 ++++++++++----------- 1 file changed, 10 insertions(+), 11 deletions(-) diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index 3bcea0baddab..2e24a97be624 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -37,17 +37,21 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, return 0; } +static unsigned long get_freq(struct msm_gpu *gpu) +{ + if (gpu->funcs->gpu_get_freq) + return gpu->funcs->gpu_get_freq(gpu); + + return clk_get_rate(gpu->core_clk); +} + static int msm_devfreq_get_dev_status(struct device *dev, struct devfreq_dev_status *status) { struct msm_gpu *gpu = dev_to_gpu(dev); ktime_t time; - if (gpu->funcs->gpu_get_freq) - status->current_frequency = gpu->funcs->gpu_get_freq(gpu); - else - status->current_frequency = clk_get_rate(gpu->core_clk); - + status->current_frequency = get_freq(gpu); status->busy_time = gpu->funcs->gpu_busy(gpu); time = ktime_get(); @@ -59,12 +63,7 @@ static int msm_devfreq_get_dev_status(struct device *dev, static int msm_devfreq_get_cur_freq(struct device *dev, unsigned long *freq) { - struct msm_gpu *gpu = dev_to_gpu(dev); - - if (gpu->funcs->gpu_get_freq) - *freq = gpu->funcs->gpu_get_freq(gpu); - else - *freq = clk_get_rate(gpu->core_clk); + *freq = get_freq(dev_to_gpu(dev)); return 0; } From patchwork Mon Jul 26 14:46:50 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 485907 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=-15.7 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,FREEMAIL_FORGED_FROMDOMAIN,FREEMAIL_FROM, 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 A0469C4338F for ; Mon, 26 Jul 2021 14:42:52 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 7CA0C60F55 for ; Mon, 26 Jul 2021 14:42:52 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S234706AbhGZOCW (ORCPT ); Mon, 26 Jul 2021 10:02:22 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:60550 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S234682AbhGZOCW (ORCPT ); Mon, 26 Jul 2021 10:02:22 -0400 Received: from mail-pj1-x102f.google.com (mail-pj1-x102f.google.com [IPv6:2607:f8b0:4864:20::102f]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id ADFEBC061757; Mon, 26 Jul 2021 07:42:50 -0700 (PDT) Received: by mail-pj1-x102f.google.com with SMTP id e2-20020a17090a4a02b029016f3020d867so297953pjh.3; Mon, 26 Jul 2021 07:42:50 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=from:to:cc:subject:date:message-id:in-reply-to:references :mime-version:content-transfer-encoding; bh=Rlta0NEovcclpaPJpD2xtS9yg3zCeqF6l6C6xl/bEnk=; b=MXQvlm5f7NTlQFcq3MkDZlFoTbSB2ULWsD6K+q14oA0GkYqM4+ZHwtjr/XT0wPmsN9 58obxREMteJ8Y05M6NgoXSKtfShL+iWJcy+YYGMXgokoSLKT9161DNf/+ylDyM0dJixe maG6+qAjJa0pMkhlMfISxJRYx8cBtwLnmnCHP7B2jT0rqXXlGVZUaqi9UreTy543Zgz+ A78ucVm7QM46p4KW9Hgpa+QcEt7vYEL8FsqCNRTt1WXbWQh8i75qXPWYqQxMQqVT7hhk L7Gf/4CmAXhe7UGG5hRsRfRrJPNgPBtEJEqlPZXL048WzRIF67SL67Fm82fU3vfiSrnO JWwA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-transfer-encoding; bh=Rlta0NEovcclpaPJpD2xtS9yg3zCeqF6l6C6xl/bEnk=; b=lGVkri8hD2qrP5XyhKQwsXV1dP25EMneL1sl81/6o7c1FHuazo62NUptNrr6Zee32j pFZgCCyCvSpeWqvF1KSPbnIyQbc32M9eCEAPZb7OdKjRmMn/djSAnJBlyegWDgAjMhqi LGlRFve5lEiiipmhyjtuTq+ksKd7RZZ85k/2Yl1RgYxgngfb54HBgToM95IwMdlWb0Wl f/Sn+g2CoWkoY285nuzdYJ7PPOLE79UqpI7wmb3E+2vwDAxSUDHRa5A+/Ju+YECR/r9B utUqO0vMgiXSfbp3G1uAY16GlAHvvItI8eadZxeqrZsjo8fcxMCojHh6r738ISJjAgex XmSw== X-Gm-Message-State: AOAM531KzivkrDJdHkfBaJIjmVylVtdjlcKIi3MuwF/jQPxCsCPnFITy eLu+MECVFmTpqUm3LYdQZ0E= X-Google-Smtp-Source: ABdhPJwvV+Ta7Aed4EqK/5ZlO07y7a/xBo8shDf26JWpJt+WXH9hmPeAdzDtih6ushddXac2m2SrdQ== X-Received: by 2002:a63:354:: with SMTP id 81mr18503749pgd.369.1627310570186; Mon, 26 Jul 2021 07:42:50 -0700 (PDT) Received: from localhost ([2601:1c0:5200:a6:307:a401:7b76:c6e5]) by smtp.gmail.com with ESMTPSA id i13sm230613pfr.79.2021.07.26.07.42.48 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Mon, 26 Jul 2021 07:42:49 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: Rob Clark , Rob Clark , Sean Paul , David Airlie , Daniel Vetter , linux-arm-msm@vger.kernel.org (open list:DRM DRIVER FOR MSM ADRENO GPU), freedreno@lists.freedesktop.org (open list:DRM DRIVER FOR MSM ADRENO GPU), linux-kernel@vger.kernel.org (open list) Subject: [PATCH v2 3/3] drm/msm: Devfreq tuning Date: Mon, 26 Jul 2021 07:46:50 -0700 Message-Id: <20210726144653.2180096-4-robdclark@gmail.com> X-Mailer: git-send-email 2.31.1 In-Reply-To: <20210726144653.2180096-1-robdclark@gmail.com> References: <20210726144653.2180096-1-robdclark@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-arm-msm@vger.kernel.org From: Rob Clark This adds a few things to try and make frequency scaling better match the workload: 1) Longer polling interval to avoid whip-lashing between too-high and too-low frequencies in certain workloads, like mobile games which throttle themselves to 30fps. Previously our polling interval was short enough to let things ramp down to minimum freq in the "off" frame, but long enough to not react quickly enough when rendering started on the next frame, leading to uneven frame times. (Ie. rather than a consistent 33ms it would alternate between 16/33/48ms.) 2) Awareness of when the GPU is active vs idle. Since we know when the GPU is active vs idle, we can clamp the frequency down to the minimum while it is idle. (If it is idle for long enough, then the autosuspend delay will eventually kick in and power down the GPU.) Since devfreq has no knowledge of powered-but-idle, this takes a small bit of trickery to maintain a "fake" frequency while idle. This, combined with the longer polling period allows devfreq to arrive at a reasonable "active" frequency, while still clamping to minimum freq when idle to reduce power draw. 3) Boost. Because simple_ondemand needs to see a certain threshold of busyness to ramp up, we could end up needing multiple polling cycles before it reacts appropriately on interactive workloads (ex. scrolling a web page after reading for some time), on top of the already lengthened polling interval, when we see a idle to active transition after a period of idle time we boost the frequency that we return to. Signed-off-by: Rob Clark --- drivers/gpu/drm/msm/msm_gpu.c | 16 ++++++ drivers/gpu/drm/msm/msm_gpu.h | 29 +++++++++++ drivers/gpu/drm/msm/msm_gpu_devfreq.c | 73 ++++++++++++++++++++++++++- 3 files changed, 117 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index fedbd785e42f..c4ed8694f721 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -680,6 +680,14 @@ static void retire_submit(struct msm_gpu *gpu, struct msm_ringbuffer *ring, list_del(&submit->node); spin_unlock_irqrestore(&ring->submit_lock, flags); + /* Update devfreq on transition from active->idle: */ + mutex_lock(&gpu->active_lock); + gpu->active_submits--; + WARN_ON(gpu->active_submits < 0); + if (!gpu->active_submits) + msm_devfreq_idle(gpu); + mutex_unlock(&gpu->active_lock); + msm_gem_submit_put(submit); } @@ -781,6 +789,13 @@ void msm_gpu_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) list_add_tail(&submit->node, &ring->submits); spin_unlock_irqrestore(&ring->submit_lock, flags); + /* Update devfreq on transition from idle->active: */ + mutex_lock(&gpu->active_lock); + if (!gpu->active_submits) + msm_devfreq_active(gpu); + gpu->active_submits++; + mutex_unlock(&gpu->active_lock); + gpu->funcs->submit(gpu, submit); priv->lastctx = submit->queue->ctx; @@ -866,6 +881,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, sched_set_fifo_low(gpu->worker->task); INIT_LIST_HEAD(&gpu->active_list); + mutex_init(&gpu->active_lock); kthread_init_work(&gpu->retire_work, retire_worker); kthread_init_work(&gpu->recover_work, recover_worker); kthread_init_work(&gpu->fault_work, fault_worker); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 2e61d05293e6..710c3fedfbf3 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -98,6 +98,20 @@ struct msm_gpu_devfreq { /** time: Time of last sampling period. */ ktime_t time; + + /** idle_time: Time of last transition to idle: */ + ktime_t idle_time; + + /** + * idle_freq: + * + * Shadow frequency used while the GPU is idle. From the PoV of + * the devfreq governor, we are continuing to sample busyness and + * adjust frequency while the GPU is idle, but we use this shadow + * value as the GPU is actually clamped to minimum frequency while + * it is inactive. + */ + unsigned long idle_freq; }; struct msm_gpu { @@ -129,6 +143,19 @@ struct msm_gpu { */ struct list_head active_list; + /** + * active_submits: + * + * The number of submitted but not yet retired submits, used to + * determine transitions between active and idle. + * + * Protected by lock + */ + int active_submits; + + /** lock: protects active_submits and idle/active transitions */ + struct mutex active_lock; + /* does gpu need hw_init? */ bool needs_hw_init; @@ -322,6 +349,8 @@ void msm_devfreq_init(struct msm_gpu *gpu); void msm_devfreq_cleanup(struct msm_gpu *gpu); void msm_devfreq_resume(struct msm_gpu *gpu); void msm_devfreq_suspend(struct msm_gpu *gpu); +void msm_devfreq_active(struct msm_gpu *gpu); +void msm_devfreq_idle(struct msm_gpu *gpu); int msm_gpu_hw_init(struct msm_gpu *gpu); diff --git a/drivers/gpu/drm/msm/msm_gpu_devfreq.c b/drivers/gpu/drm/msm/msm_gpu_devfreq.c index 2e24a97be624..0a1ee20296a2 100644 --- a/drivers/gpu/drm/msm/msm_gpu_devfreq.c +++ b/drivers/gpu/drm/msm/msm_gpu_devfreq.c @@ -22,6 +22,15 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, opp = devfreq_recommended_opp(dev, freq, flags); + /* + * If the GPU is idle, devfreq is not aware, so just ignore + * it's requests + */ + if (gpu->devfreq.idle_freq) { + gpu->devfreq.idle_freq = *freq; + return 0; + } + if (IS_ERR(opp)) return PTR_ERR(opp); @@ -39,6 +48,9 @@ static int msm_devfreq_target(struct device *dev, unsigned long *freq, static unsigned long get_freq(struct msm_gpu *gpu) { + if (gpu->devfreq.idle_freq) + return gpu->devfreq.idle_freq; + if (gpu->funcs->gpu_get_freq) return gpu->funcs->gpu_get_freq(gpu); @@ -69,7 +81,8 @@ static int msm_devfreq_get_cur_freq(struct device *dev, unsigned long *freq) } static struct devfreq_dev_profile msm_devfreq_profile = { - .polling_ms = 10, + .timer = DEVFREQ_TIMER_DELAYED, + .polling_ms = 50, .target = msm_devfreq_target, .get_dev_status = msm_devfreq_get_dev_status, .get_cur_freq = msm_devfreq_get_cur_freq, @@ -130,3 +143,61 @@ void msm_devfreq_suspend(struct msm_gpu *gpu) { devfreq_suspend_device(gpu->devfreq.devfreq); } + +void msm_devfreq_active(struct msm_gpu *gpu) +{ + struct msm_gpu_devfreq *df = &gpu->devfreq; + struct devfreq_dev_status status; + unsigned int idle_time; + unsigned long target_freq = df->idle_freq; + + /* + * Hold devfreq lock to synchronize with get_dev_status()/ + * target() callbacks + */ + mutex_lock(&df->devfreq->lock); + + idle_time = ktime_to_ms(ktime_sub(ktime_get(), df->idle_time)); + + /* + * If we've been idle for a significant fraction of a polling + * interval, then we won't meet the threshold of busyness for + * the governor to ramp up the freq.. so give some boost + */ + if (idle_time > msm_devfreq_profile.polling_ms/2) { + target_freq *= 2; + } + + df->idle_freq = 0; + + msm_devfreq_target(&gpu->pdev->dev, &target_freq, 0); + + /* + * Reset the polling interval so we aren't inconsistent + * about freq vs busy/total cycles + */ + msm_devfreq_get_dev_status(&gpu->pdev->dev, &status); + + mutex_unlock(&df->devfreq->lock); +} + +void msm_devfreq_idle(struct msm_gpu *gpu) +{ + struct msm_gpu_devfreq *df = &gpu->devfreq; + unsigned long idle_freq, target_freq = 0; + + /* + * Hold devfreq lock to synchronize with get_dev_status()/ + * target() callbacks + */ + mutex_lock(&df->devfreq->lock); + + idle_freq = get_freq(gpu); + + msm_devfreq_target(&gpu->pdev->dev, &target_freq, 0); + + df->idle_time = ktime_get(); + df->idle_freq = idle_freq; + + mutex_unlock(&df->devfreq->lock); +}