From patchwork Sat May 20 12:19:50 2023 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Konrad Dybcio X-Patchwork-Id: 13249215 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 gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 00FAAC7EE29 for ; Sat, 20 May 2023 12:20:21 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 452B110E17F; Sat, 20 May 2023 12:20:09 +0000 (UTC) Received: from mail-lf1-x129.google.com (mail-lf1-x129.google.com [IPv6:2a00:1450:4864:20::129]) by gabe.freedesktop.org (Postfix) with ESMTPS id DA2ED10E16F for ; Sat, 20 May 2023 12:20:05 +0000 (UTC) Received: by mail-lf1-x129.google.com with SMTP id 2adb3069b0e04-4f27977aed6so4678780e87.2 for ; Sat, 20 May 2023 05:20:05 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linaro.org; s=google; t=1684585204; x=1687177204; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:from:to:cc:subject:date:message-id :reply-to; bh=r42OHg5sw6USQpav+QAtLIHSfv+s6K21VPjaJ87fp6k=; b=LHBMGFFlg/r0+uhsaf99LJIF+ugKhbGkbRvvttQtUw2Reca8wx8bOa1TtshkZi1GFK F7rRDzsMRUmLRt8fyQbWSyufSAqpYnHM/rwCZ1v9Xj0nRDXUbWmckClwKZUQmQVeHPfd OjEWCiffMHG9LxoHBNceUmZBXzoAgxl9VDPjhXEvc1rTjdvlQbS1xq4AZJmgha67FFzP msfvRMkLPxVCek6xsXTty1a/t8BJZLVKuoxPuw2MGHwBbgvmmkyQhzRzsYYcNifDwMKM trZPc2y5Ym/yIRz82JzLAW17UHiDl2m6Fa8ulJ4FxjOEBFpZzixT0xKZSNQSYxxIL4Et zy7w== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20221208; t=1684585204; x=1687177204; h=cc:to:in-reply-to:references:message-id:content-transfer-encoding :mime-version:subject:date:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=r42OHg5sw6USQpav+QAtLIHSfv+s6K21VPjaJ87fp6k=; b=hiQKUsrZ7Emzy+FQAbuTYJLrMfcq2bDAu211tG8xAOuPYFmRAjBwrr6yRoz51rI4rE 3efHd2V/n+VRCbS+NGSGBgDhTL2YD/b6I7UxqXn9mOrRSBlLZ8xYFcU0/o0LE4URrbCh RlKCJa6dk8gFDFfRxlWV+Bo0D1n1A3Psqxr8S4Ryv+bQU2jC3M5JLBEw7L9km+xYXgrU sUXR8rXpo32XvOWojOk1SI/xjDywUFfLmBjJxIQxRLwOtrBu8XbltvFWE8XOVHhAixCd skaQ7w+rNYzdWPzvHY/hWJzH3pGjIM/LU+lToUHTxo0B8BtBR9wmYXLK4NHMTcmGCrfQ PDhw== X-Gm-Message-State: AC+VfDy3JS9SjjQ0UwmeUtAwWt8Gy/njKdT1t1CMMEaFD9BKdqmDIQCf xhH9Z7Y2kVo5quMUmvxqFuZhFheZqsKoBX5HnO0= X-Google-Smtp-Source: ACHHUZ6mT+1dOGQQrI5Uu0SOp6BDaLD8u5qIjDyu62DOPHjC0k4O0UVGWyVc+fFxPWLk40awEspXiA== X-Received: by 2002:ac2:555e:0:b0:4f3:880b:285a with SMTP id l30-20020ac2555e000000b004f3880b285amr1903948lfk.29.1684585203804; Sat, 20 May 2023 05:20:03 -0700 (PDT) Received: from [192.168.1.101] (abxi58.neoplus.adsl.tpnet.pl. [83.9.2.58]) by smtp.gmail.com with ESMTPSA id y6-20020ac24466000000b004f37bd02a89sm244766lfl.287.2023.05.20.05.20.02 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Sat, 20 May 2023 05:20:03 -0700 (PDT) From: Konrad Dybcio Date: Sat, 20 May 2023 14:19:50 +0200 Subject: [PATCH v7 10/18] drm/msm/a6xx: Introduce GMU wrapper support MIME-Version: 1.0 Message-Id: <20230223-topic-gmuwrapper-v7-10-ecc7aab83556@linaro.org> References: <20230223-topic-gmuwrapper-v7-0-ecc7aab83556@linaro.org> In-Reply-To: <20230223-topic-gmuwrapper-v7-0-ecc7aab83556@linaro.org> To: Rob Clark , Abhinav Kumar , Dmitry Baryshkov , Sean Paul , David Airlie , Daniel Vetter , Rob Herring , Krzysztof Kozlowski , Bjorn Andersson , Konrad Dybcio , Akhil P Oommen X-Mailer: b4 0.12.2 X-Developer-Signature: v=1; a=ed25519-sha256; t=1684585186; l=19516; i=konrad.dybcio@linaro.org; s=20230215; h=from:subject:message-id; bh=88uNcwZzh+SW7+WRWKcfYA0V+uRhojonVpikMRa9F0Y=; b=f0mWmHaD1/Y8gTbXf1bX/aqN2vj7JjjgPhQRI5Z8JNfDEbafRqvA/fG8a44Ih7bjGWe6BDgr8 YvKYLfhpNZIBvHqrGIg7oVLO9Xjh30evYdzcfZTt8k5xhR5H8QWx5Pm X-Developer-Key: i=konrad.dybcio@linaro.org; a=ed25519; pk=iclgkYvtl2w05SSXO5EjjSYlhFKsJ+5OSZBjOkQuEms= X-BeenThere: dri-devel@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Direct Rendering Infrastructure - Development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Rob Clark , devicetree@vger.kernel.org, linux-arm-msm@vger.kernel.org, linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org, Konrad Dybcio , Marijn Suijten , freedreno@lists.freedesktop.org Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" Some (particularly SMD_RPM, a.k.a non-RPMh) SoCs implement A6XX GPUs but don't implement the associated GMUs. This is due to the fact that the GMU directly pokes at RPMh. Sadly, this means we have to take care of enabling & scaling power rails, clocks and bandwidth ourselves. Reuse existing Adreno-common code and modify the deeply-GMU-infused A6XX code to facilitate these GPUs. This involves if-ing out lots of GMU callbacks and introducing a new type of GMU - GMU wrapper (it's the actual name that Qualcomm uses in their downstream kernels). This is essentially a register region which is convenient to model as a device. We'll use it for managing the GDSCs. The register layout matches the actual GMU_CX/GX regions on the "real GMU" devices and lets us reuse quite a bit of gmu_read/write/rmw calls. Signed-off-by: Konrad Dybcio --- drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 72 +++++++++- drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 215 ++++++++++++++++++++++++---- drivers/gpu/drm/msm/adreno/a6xx_gpu.h | 1 + drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 14 +- drivers/gpu/drm/msm/adreno/adreno_gpu.c | 8 +- drivers/gpu/drm/msm/adreno/adreno_gpu.h | 6 + 6 files changed, 281 insertions(+), 35 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c index 5ba8cba69383..385ca3a12462 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c @@ -1437,6 +1437,7 @@ static int a6xx_gmu_get_irq(struct a6xx_gmu *gmu, struct platform_device *pdev, void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu) { + struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; struct a6xx_gmu *gmu = &a6xx_gpu->gmu; struct platform_device *pdev = to_platform_device(gmu->dev); @@ -1462,10 +1463,12 @@ void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu) gmu->mmio = NULL; gmu->rscc = NULL; - a6xx_gmu_memory_free(gmu); + if (!adreno_has_gmu_wrapper(adreno_gpu)) { + a6xx_gmu_memory_free(gmu); - free_irq(gmu->gmu_irq, gmu); - free_irq(gmu->hfi_irq, gmu); + free_irq(gmu->gmu_irq, gmu); + free_irq(gmu->hfi_irq, gmu); + } /* Drop reference taken in of_find_device_by_node */ put_device(gmu->dev); @@ -1484,6 +1487,69 @@ static int cxpd_notifier_cb(struct notifier_block *nb, return 0; } +int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) +{ + struct platform_device *pdev = of_find_device_by_node(node); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + int ret; + + if (!pdev) + return -ENODEV; + + gmu->dev = &pdev->dev; + + of_dma_configure(gmu->dev, node, true); + + pm_runtime_enable(gmu->dev); + + /* Mark legacy for manual SPTPRAC control */ + gmu->legacy = true; + + /* Map the GMU registers */ + gmu->mmio = a6xx_gmu_get_mmio(pdev, "gmu"); + if (IS_ERR(gmu->mmio)) { + ret = PTR_ERR(gmu->mmio); + goto err_mmio; + } + + gmu->cxpd = dev_pm_domain_attach_by_name(gmu->dev, "cx"); + if (IS_ERR(gmu->cxpd)) { + ret = PTR_ERR(gmu->cxpd); + goto err_mmio; + } + + if (!device_link_add(gmu->dev, gmu->cxpd, DL_FLAG_PM_RUNTIME)) { + ret = -ENODEV; + goto detach_cxpd; + } + + init_completion(&gmu->pd_gate); + complete_all(&gmu->pd_gate); + gmu->pd_nb.notifier_call = cxpd_notifier_cb; + + /* Get a link to the GX power domain to reset the GPU */ + gmu->gxpd = dev_pm_domain_attach_by_name(gmu->dev, "gx"); + if (IS_ERR(gmu->gxpd)) { + ret = PTR_ERR(gmu->gxpd); + goto err_mmio; + } + + gmu->initialized = true; + + return 0; + +detach_cxpd: + dev_pm_domain_detach(gmu->cxpd, false); + +err_mmio: + iounmap(gmu->mmio); + + /* Drop reference taken in of_find_device_by_node */ + put_device(gmu->dev); + + return ret; +} + int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node) { struct adreno_gpu *adreno_gpu = &a6xx_gpu->base; diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 58bf405b85d8..2ba9d790a52c 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -21,7 +21,7 @@ static inline bool _a6xx_check_idle(struct msm_gpu *gpu) struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); /* Check that the GMU is idle */ - if (!a6xx_gmu_isidle(&a6xx_gpu->gmu)) + if (!adreno_has_gmu_wrapper(adreno_gpu) && !a6xx_gmu_isidle(&a6xx_gpu->gmu)) return false; /* Check tha the CX master is idle */ @@ -1018,10 +1018,13 @@ static int hw_init(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; int ret; - /* Make sure the GMU keeps the GPU on while we set it up */ - a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + if (!adreno_has_gmu_wrapper(adreno_gpu)) { + /* Make sure the GMU keeps the GPU on while we set it up */ + a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_GPU_SET); + } /* Clear GBIF halt in case GX domain was not collapsed */ if (a6xx_has_gbif(adreno_gpu)) { @@ -1148,6 +1151,17 @@ static int hw_init(struct msm_gpu *gpu) 0x3f0243f0); } + if (adreno_has_gmu_wrapper(adreno_gpu)) { + /* Do it here, as GMU wrapper only inits the GMU for memory reservation etc. */ + + /* Set up the CX GMU counter 0 to count busy ticks */ + gmu_write(gmu, REG_A6XX_GPU_GMU_AO_GPU_CX_BUSY_MASK, 0xff000000); + + /* Enable power counter 0 */ + gmu_rmw(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_SELECT_0, 0xff, BIT(5)); + gmu_write(gmu, REG_A6XX_GMU_CX_GMU_POWER_COUNTER_ENABLE, 1); + } + /* Protect registers from the CP */ a6xx_set_cp_protect(gpu); @@ -1237,6 +1251,8 @@ static int hw_init(struct msm_gpu *gpu) } out: + if (adreno_has_gmu_wrapper(adreno_gpu)) + return ret; /* * Tell the GMU that we are done touching the GPU and it can start power * management @@ -1271,9 +1287,6 @@ static void a6xx_dump(struct msm_gpu *gpu) adreno_dump(gpu); } -#define VBIF_RESET_ACK_TIMEOUT 100 -#define VBIF_RESET_ACK_MASK 0x00f0 - static void a6xx_recover(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -1311,6 +1324,15 @@ static void a6xx_recover(struct msm_gpu *gpu) */ gpu->active_submits = 0; + if (adreno_has_gmu_wrapper(adreno_gpu)) { + /* Drain the outstanding traffic on memory buses */ + a6xx_bus_clear_pending_transactions(adreno_gpu, true); + + /* Reset the GPU to a clean state */ + a6xx_gpu_sw_reset(gpu, true); + a6xx_gpu_sw_reset(gpu, false); + } + reinit_completion(&gmu->pd_gate); dev_pm_genpd_add_notifier(gmu->cxpd, &gmu->pd_nb); dev_pm_genpd_synced_poweroff(gmu->cxpd); @@ -1461,7 +1483,8 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) * Force the GPU to stay on until after we finish * collecting information */ - gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 1); + if (!adreno_has_gmu_wrapper(adreno_gpu)) + gmu_write(&a6xx_gpu->gmu, REG_A6XX_GMU_GMU_PWR_COL_KEEPALIVE, 1); DRM_DEV_ERROR(&gpu->pdev->dev, "gpu fault ring %d fence %x status %8.8X rb %4.4x/%4.4x ib1 %16.16llX/%4.4x ib2 %16.16llX/%4.4x\n", @@ -1592,6 +1615,10 @@ static void a6xx_llc_activate(struct a6xx_gpu *a6xx_gpu) static void a6xx_llc_slices_destroy(struct a6xx_gpu *a6xx_gpu) { + /* No LLCC on non-RPMh (and by extension, non-GMU) SoCs */ + if (adreno_has_gmu_wrapper(&a6xx_gpu->base)) + return; + llcc_slice_putd(a6xx_gpu->llc_slice); llcc_slice_putd(a6xx_gpu->htw_llc_slice); } @@ -1601,6 +1628,10 @@ static void a6xx_llc_slices_init(struct platform_device *pdev, { struct device_node *phandle; + /* No LLCC on non-RPMh (and by extension, non-GMU) SoCs */ + if (adreno_has_gmu_wrapper(&a6xx_gpu->base)) + return; + /* * There is a different programming path for targets with an mmu500 * attached, so detect if that is the case @@ -1670,7 +1701,7 @@ void a6xx_gpu_sw_reset(struct msm_gpu *gpu, bool assert) udelay(100); } -static int a6xx_pm_resume(struct msm_gpu *gpu) +static int a6xx_gmu_pm_resume(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); @@ -1690,10 +1721,61 @@ static int a6xx_pm_resume(struct msm_gpu *gpu) a6xx_llc_activate(a6xx_gpu); - return 0; + return ret; } -static int a6xx_pm_suspend(struct msm_gpu *gpu) +static int a6xx_pm_resume(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + unsigned long freq = 0; + struct dev_pm_opp *opp; + int ret; + + gpu->needs_hw_init = true; + + trace_msm_gpu_resume(0); + + mutex_lock(&a6xx_gpu->gmu.lock); + + pm_runtime_resume_and_get(gmu->dev); + pm_runtime_resume_and_get(gmu->gxpd); + + /* Set the core clock, having VDD scaling in mind */ + ret = dev_pm_opp_set_rate(&gpu->pdev->dev, gpu->fast_rate); + if (ret) + goto err_core_clk; + + ret = clk_bulk_prepare_enable(gpu->nr_clocks, gpu->grp_clks); + if (ret) + goto err_bulk_clk; + + ret = clk_prepare_enable(gpu->ebi1_clk); + if (ret) + goto err_mem_clk; + + /* If anything goes south, tear the GPU down piece by piece.. */ + if (ret) { +err_mem_clk: + clk_bulk_disable_unprepare(gpu->nr_clocks, gpu->grp_clks); +err_bulk_clk: + opp = dev_pm_opp_find_freq_ceil(&gpu->pdev->dev, &freq); + dev_pm_opp_put(opp); + dev_pm_opp_set_rate(&gpu->pdev->dev, 0); +err_core_clk: + pm_runtime_put(gmu->gxpd); + pm_runtime_put(gmu->dev); + } + mutex_unlock(&a6xx_gpu->gmu.lock); + + if (!ret) + msm_devfreq_resume(gpu); + + return ret; +} + +static int a6xx_gmu_pm_suspend(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); @@ -1720,7 +1802,41 @@ static int a6xx_pm_suspend(struct msm_gpu *gpu) return 0; } -static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) +static int a6xx_pm_suspend(struct msm_gpu *gpu) +{ + struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); + struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); + struct a6xx_gmu *gmu = &a6xx_gpu->gmu; + int i; + + trace_msm_gpu_suspend(0); + + msm_devfreq_suspend(gpu); + + mutex_lock(&a6xx_gpu->gmu.lock); + + /* Drain the outstanding traffic on memory buses */ + a6xx_bus_clear_pending_transactions(adreno_gpu, true); + + clk_disable_unprepare(gpu->ebi1_clk); + + clk_bulk_disable_unprepare(gpu->nr_clocks, gpu->grp_clks); + + pm_runtime_put_sync(gmu->gxpd); + pm_runtime_put_sync(gmu->dev); + + mutex_unlock(&a6xx_gpu->gmu.lock); + + if (a6xx_gpu->shadow_bo) + for (i = 0; i < gpu->nr_rings; i++) + a6xx_gpu->shadow[i] = 0; + + gpu->suspend_count++; + + return 0; +} + +static int a6xx_gmu_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu); @@ -1739,6 +1855,12 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) return 0; } +static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) +{ + *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER); + return 0; +} + static struct msm_ringbuffer *a6xx_active_ring(struct msm_gpu *gpu) { struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu); @@ -2004,8 +2126,8 @@ static const struct adreno_gpu_funcs funcs = { .set_param = adreno_set_param, .hw_init = a6xx_hw_init, .ucode_load = a6xx_ucode_load, - .pm_suspend = a6xx_pm_suspend, - .pm_resume = a6xx_pm_resume, + .pm_suspend = a6xx_gmu_pm_suspend, + .pm_resume = a6xx_gmu_pm_resume, .recover = a6xx_recover, .submit = a6xx_submit, .active_ring = a6xx_active_ring, @@ -2020,6 +2142,35 @@ static const struct adreno_gpu_funcs funcs = { #if defined(CONFIG_DRM_MSM_GPU_STATE) .gpu_state_get = a6xx_gpu_state_get, .gpu_state_put = a6xx_gpu_state_put, +#endif + .create_address_space = a6xx_create_address_space, + .create_private_address_space = a6xx_create_private_address_space, + .get_rptr = a6xx_get_rptr, + .progress = a6xx_progress, + }, + .get_timestamp = a6xx_gmu_get_timestamp, +}; + +static const struct adreno_gpu_funcs funcs_gmuwrapper = { + .base = { + .get_param = adreno_get_param, + .set_param = adreno_set_param, + .hw_init = a6xx_hw_init, + .ucode_load = a6xx_ucode_load, + .pm_suspend = a6xx_pm_suspend, + .pm_resume = a6xx_pm_resume, + .recover = a6xx_recover, + .submit = a6xx_submit, + .active_ring = a6xx_active_ring, + .irq = a6xx_irq, + .destroy = a6xx_destroy, +#if defined(CONFIG_DRM_MSM_GPU_STATE) + .show = a6xx_show, +#endif + .gpu_busy = a6xx_gpu_busy, +#if defined(CONFIG_DRM_MSM_GPU_STATE) + .gpu_state_get = a6xx_gpu_state_get, + .gpu_state_put = a6xx_gpu_state_put, #endif .create_address_space = a6xx_create_address_space, .create_private_address_space = a6xx_create_private_address_space, @@ -2050,15 +2201,31 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) adreno_gpu->registers = NULL; + /* Check if there is a GMU phandle and set it up */ + node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0); + /* FIXME: How do we gracefully handle this? */ + BUG_ON(!node); + + adreno_gpu->gmu_is_wrapper = of_device_is_compatible(node, "qcom,adreno-gmu-wrapper"); + /* * We need to know the platform type before calling into adreno_gpu_init * so that the hw_apriv flag can be correctly set. Snoop into the info * and grab the revision number */ info = adreno_info(config->rev); - - if (info && (info->revn == 650 || info->revn == 660 || - adreno_cmp_rev(ADRENO_REV(6, 3, 5, ANY_ID), info->rev))) + if (!info) + return ERR_PTR(-EINVAL); + + /* Assign these early so that we can use the is_aXYZ helpers */ + /* Numeric revision IDs (e.g. 630) */ + adreno_gpu->revn = info->revn; + /* New-style ADRENO_REV()-only */ + adreno_gpu->rev = info->rev; + /* Quirk data */ + adreno_gpu->info = info; + + if (adreno_is_a650(adreno_gpu) || adreno_is_a660_family(adreno_gpu)) adreno_gpu->base.hw_apriv = true; a6xx_llc_slices_init(pdev, a6xx_gpu); @@ -2069,7 +2236,10 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) return ERR_PTR(ret); } - ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); + if (adreno_has_gmu_wrapper(adreno_gpu)) + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs_gmuwrapper, 1); + else + ret = adreno_gpu_init(dev, pdev, adreno_gpu, &funcs, 1); if (ret) { a6xx_destroy(&(a6xx_gpu->base.base)); return ERR_PTR(ret); @@ -2082,13 +2252,10 @@ struct msm_gpu *a6xx_gpu_init(struct drm_device *dev) if (adreno_is_a618(adreno_gpu) || adreno_is_7c3(adreno_gpu)) priv->gpu_clamp_to_idle = true; - /* Check if there is a GMU phandle and set it up */ - node = of_parse_phandle(pdev->dev.of_node, "qcom,gmu", 0); - - /* FIXME: How do we gracefully handle this? */ - BUG_ON(!node); - - ret = a6xx_gmu_init(a6xx_gpu, node); + if (adreno_has_gmu_wrapper(adreno_gpu)) + ret = a6xx_gmu_wrapper_init(a6xx_gpu, node); + else + ret = a6xx_gmu_init(a6xx_gpu, node); of_node_put(node); if (ret) { a6xx_destroy(&(a6xx_gpu->base.base)); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h index aa70390ee1c6..c788b06e72da 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.h +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.h @@ -76,6 +76,7 @@ int a6xx_gmu_set_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state); void a6xx_gmu_clear_oob(struct a6xx_gmu *gmu, enum a6xx_gmu_oob_state state); int a6xx_gmu_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node); +int a6xx_gmu_wrapper_init(struct a6xx_gpu *a6xx_gpu, struct device_node *node); void a6xx_gmu_remove(struct a6xx_gpu *a6xx_gpu); void a6xx_gmu_set_freq(struct msm_gpu *gpu, struct dev_pm_opp *opp, diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index 30ecdff363e7..4e5d650578c6 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -1041,16 +1041,18 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu) /* Get the generic state from the adreno core */ adreno_gpu_state_get(gpu, &a6xx_state->base); - a6xx_get_gmu_registers(gpu, a6xx_state); + if (!adreno_has_gmu_wrapper(adreno_gpu)) { + a6xx_get_gmu_registers(gpu, a6xx_state); - a6xx_state->gmu_log = a6xx_snapshot_gmu_bo(a6xx_state, &a6xx_gpu->gmu.log); - a6xx_state->gmu_hfi = a6xx_snapshot_gmu_bo(a6xx_state, &a6xx_gpu->gmu.hfi); - a6xx_state->gmu_debug = a6xx_snapshot_gmu_bo(a6xx_state, &a6xx_gpu->gmu.debug); + a6xx_state->gmu_log = a6xx_snapshot_gmu_bo(a6xx_state, &a6xx_gpu->gmu.log); + a6xx_state->gmu_hfi = a6xx_snapshot_gmu_bo(a6xx_state, &a6xx_gpu->gmu.hfi); + a6xx_state->gmu_debug = a6xx_snapshot_gmu_bo(a6xx_state, &a6xx_gpu->gmu.debug); - a6xx_snapshot_gmu_hfi_history(gpu, a6xx_state); + a6xx_snapshot_gmu_hfi_history(gpu, a6xx_state); + } /* If GX isn't on the rest of the data isn't going to be accessible */ - if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) + if (!adreno_has_gmu_wrapper(adreno_gpu) && !a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) return &a6xx_state->base; /* Get the banks of indexed registers */ diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c index 6934cee07d42..5c5901d65950 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c @@ -528,6 +528,10 @@ int adreno_load_fw(struct adreno_gpu *adreno_gpu) if (!adreno_gpu->info->fw[i]) continue; + /* Skip loading GMU firwmare with GMU Wrapper */ + if (adreno_has_gmu_wrapper(adreno_gpu) && i == ADRENO_FW_GMU) + continue; + /* Skip if the firmware has already been loaded */ if (adreno_gpu->fw[i]) continue; @@ -1074,8 +1078,8 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev, u32 speedbin; int ret; - /* Only handle the core clock when GMU is not in use */ - if (config->rev.core < 6) { + /* Only handle the core clock when GMU is not in use (or is absent). */ + if (adreno_has_gmu_wrapper(adreno_gpu) || config->rev.core < 6) { /* * This can only be done before devm_pm_opp_of_add_table(), or * dev_pm_opp_set_config() will WARN_ON() diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h index f62612a5c70f..ee5352bc5329 100644 --- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h +++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h @@ -115,6 +115,7 @@ struct adreno_gpu { * code (a3xx_gpu.c) and stored in this common location. */ const unsigned int *reg_offsets; + bool gmu_is_wrapper; }; #define to_adreno_gpu(x) container_of(x, struct adreno_gpu, base) @@ -145,6 +146,11 @@ struct adreno_platform_config { bool adreno_cmp_rev(struct adreno_rev rev1, struct adreno_rev rev2); +static inline bool adreno_has_gmu_wrapper(struct adreno_gpu *gpu) +{ + return gpu->gmu_is_wrapper; +} + static inline bool adreno_is_a2xx(struct adreno_gpu *gpu) { return (gpu->revn < 300);