From patchwork Fri Nov 4 15:08:38 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 621405 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 844D6C43217 for ; Fri, 4 Nov 2022 15:08:37 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S231920AbiKDPIg (ORCPT ); Fri, 4 Nov 2022 11:08:36 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52538 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232360AbiKDPId (ORCPT ); Fri, 4 Nov 2022 11:08:33 -0400 Received: from mail-pj1-x102b.google.com (mail-pj1-x102b.google.com [IPv6:2607:f8b0:4864:20::102b]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id A077A2BDA; Fri, 4 Nov 2022 08:08:31 -0700 (PDT) Received: by mail-pj1-x102b.google.com with SMTP id u8-20020a17090a5e4800b002106dcdd4a0so8489467pji.1; Fri, 04 Nov 2022 08:08:31 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=l67drlOMjlbuXUK5so1ZjMU1uw6TeoDS8wjlIGiLg9o=; b=BuiGbfwr4O7X4q4peKVTr4G2GpMdkPIraxMN5KWO5IPTFBoXHk4X3mFnER9UE9vNRU nsqEUHjKdujfuZ6OzGKoOhwpoLamqmY7SzDi9VNJDH5j3gIA/eWH+A3L/O7apTd2zqwk j1YW+bn2KmWlvWzrRWMeN6rNZwRyn5xlvc35U4xcHqeFYM4joYIxboIub/vM0AIyvFZm VTCJjUzEcUD9Q/gYe4X20jy+8e2yyH/g9YJE300BGHj3ZoaPrXmMMJnd4yQhHlBcf1La BCXnoYyvVxPD1EgJtNfvwf1wNlDE6q9h/MVUUsSWkVdmTj7Px0YbCvrm2nEk+Xz7A7gv ygAA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=l67drlOMjlbuXUK5so1ZjMU1uw6TeoDS8wjlIGiLg9o=; b=7+/3JmgqYl5CNEZ/haBODJVOmHNqrqKgGArUzQeaoGCRzRy9a6+DVGMb5LQtNsHl00 ZCPYI1Q9f5SgTQ1KOaoBpm2tbCuvIvRihFHXrv40mxQLxTmvS+0iVA7gyCGm/cZAXwNE gtJUenheKnuO9+ER/9F9bSgCBv41BL0l59NZax/UN/uOPMv4ZZAR4/S0iTL5hZFI2x4L 4SgiAOIGRx/hG7SDtID0Dyko7rVwn9glkDrdbLf89t5FGOo2fPrL+h3IXkzlVNEQHqFy OCh/j3qICUDwZ/UkmDbVdpGTOdESQ68TFdOV8Lbxpacq8wxbSrLNEr9UbYX4y0QTYqVE WG+g== X-Gm-Message-State: ACrzQf2Su4mNH37iVke8q1qqIfmFatJgMT0UBWSAiFz0Wb/DIug8Hm3J NG8kN/7w3Uct8N8k+uqVhXc= X-Google-Smtp-Source: AMsMyM7i2KfCKkrRZkbPJTyvzkQhPO06OakZRaNuM5x9fX2ilWrmGoXSinbI475LHb8sR8ypNJhpCg== X-Received: by 2002:a17:90b:1a81:b0:213:f71d:4895 with SMTP id ng1-20020a17090b1a8100b00213f71d4895mr24507040pjb.213.1667574510934; Fri, 04 Nov 2022 08:08:30 -0700 (PDT) Received: from localhost ([2a00:79e1:abd:4a00:2703:3c72:eb1a:cffd]) by smtp.gmail.com with ESMTPSA id q13-20020a63d60d000000b0046ae5cfc3d5sm2475505pgg.61.2022.11.04.08.08.30 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 04 Nov 2022 08:08:30 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: freedreno@lists.freedesktop.org, linux-arm-msm@vger.kernel.org, Rob Clark , Dmitry Baryshkov , Akhil P Oommen , Rob Clark , Abhinav Kumar , Sean Paul , David Airlie , Daniel Vetter , Vladimir Lypak , Douglas Anderson , Chia-I Wu , Konrad Dybcio , linux-kernel@vger.kernel.org (open list) Subject: [PATCH v3 1/2] drm/msm/adreno: Simplify read64/write64 helpers Date: Fri, 4 Nov 2022 08:08:38 -0700 Message-Id: <20221104150847.525173-2-robdclark@gmail.com> X-Mailer: git-send-email 2.38.1 In-Reply-To: <20221104150847.525173-1-robdclark@gmail.com> References: <20221104150847.525173-1-robdclark@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-arm-msm@vger.kernel.org From: Rob Clark The _HI reg is always following the _LO reg, so no need to pass these offsets seprately. Signed-off-by: Rob Clark Reviewed-by: Dmitry Baryshkov Reviewed-by: Akhil P Oommen --- drivers/gpu/drm/msm/adreno/a4xx_gpu.c | 3 +-- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 27 ++++++++------------- drivers/gpu/drm/msm/adreno/a5xx_preempt.c | 4 +-- drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 24 ++++++------------ drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c | 3 +-- drivers/gpu/drm/msm/msm_gpu.h | 12 ++++----- 6 files changed, 27 insertions(+), 46 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c index 7cb8d9849c07..a10feb8a4194 100644 --- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c @@ -606,8 +606,7 @@ static int a4xx_pm_suspend(struct msm_gpu *gpu) { static int a4xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { - *value = gpu_read64(gpu, REG_A4XX_RBBM_PERFCTR_CP_0_LO, - REG_A4XX_RBBM_PERFCTR_CP_0_HI); + *value = gpu_read64(gpu, REG_A4XX_RBBM_PERFCTR_CP_0_LO); return 0; } diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 3dcec7acb384..ba22d3c918bc 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -605,11 +605,9 @@ static int a5xx_ucode_init(struct msm_gpu *gpu) a5xx_ucode_check_version(a5xx_gpu, a5xx_gpu->pfp_bo); } - gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, - REG_A5XX_CP_ME_INSTR_BASE_HI, a5xx_gpu->pm4_iova); + gpu_write64(gpu, REG_A5XX_CP_ME_INSTR_BASE_LO, a5xx_gpu->pm4_iova); - gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO, - REG_A5XX_CP_PFP_INSTR_BASE_HI, a5xx_gpu->pfp_iova); + gpu_write64(gpu, REG_A5XX_CP_PFP_INSTR_BASE_LO, a5xx_gpu->pfp_iova); return 0; } @@ -868,8 +866,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) * memory rendering at this point in time and we don't want to block off * part of the virtual memory space. */ - gpu_write64(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, - REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000); + gpu_write64(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, 0x00000000); gpu_write(gpu, REG_A5XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); /* Put the GPU into 64 bit by default */ @@ -908,8 +905,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) return ret; /* Set the ringbuffer address */ - gpu_write64(gpu, REG_A5XX_CP_RB_BASE, REG_A5XX_CP_RB_BASE_HI, - gpu->rb[0]->iova); + gpu_write64(gpu, REG_A5XX_CP_RB_BASE, gpu->rb[0]->iova); /* * If the microcode supports the WHERE_AM_I opcode then we can use that @@ -936,7 +932,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu) } gpu_write64(gpu, REG_A5XX_CP_RB_RPTR_ADDR, - REG_A5XX_CP_RB_RPTR_ADDR_HI, shadowptr(a5xx_gpu, gpu->rb[0])); + shadowptr(a5xx_gpu, gpu->rb[0])); } else if (gpu->nr_rings > 1) { /* Disable preemption if WHERE_AM_I isn't available */ a5xx_preempt_fini(gpu); @@ -1239,9 +1235,9 @@ static void a5xx_fault_detect_irq(struct msm_gpu *gpu) gpu_read(gpu, REG_A5XX_RBBM_STATUS), gpu_read(gpu, REG_A5XX_CP_RB_RPTR), gpu_read(gpu, REG_A5XX_CP_RB_WPTR), - gpu_read64(gpu, REG_A5XX_CP_IB1_BASE, REG_A5XX_CP_IB1_BASE_HI), + gpu_read64(gpu, REG_A5XX_CP_IB1_BASE), gpu_read(gpu, REG_A5XX_CP_IB1_BUFSZ), - gpu_read64(gpu, REG_A5XX_CP_IB2_BASE, REG_A5XX_CP_IB2_BASE_HI), + gpu_read64(gpu, REG_A5XX_CP_IB2_BASE), gpu_read(gpu, REG_A5XX_CP_IB2_BUFSZ)); /* Turn off the hangcheck timer to keep it from bothering us */ @@ -1427,8 +1423,7 @@ static int a5xx_pm_suspend(struct msm_gpu *gpu) static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) { - *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO, - REG_A5XX_RBBM_ALWAYSON_COUNTER_HI); + *value = gpu_read64(gpu, REG_A5XX_RBBM_ALWAYSON_COUNTER_LO); return 0; } @@ -1465,8 +1460,7 @@ static int a5xx_crashdumper_run(struct msm_gpu *gpu, if (IS_ERR_OR_NULL(dumper->ptr)) return -EINVAL; - gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO, - REG_A5XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova); + gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO, dumper->iova); gpu_write(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, 1); @@ -1666,8 +1660,7 @@ static u64 a5xx_gpu_busy(struct msm_gpu *gpu, unsigned long *out_sample_rate) { u64 busy_cycles; - busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO, - REG_A5XX_RBBM_PERFCTR_RBBM_0_HI); + busy_cycles = gpu_read64(gpu, REG_A5XX_RBBM_PERFCTR_RBBM_0_LO); *out_sample_rate = clk_get_rate(gpu->core_clk); return busy_cycles; diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c index 8abc9a2b114a..7658e89844b4 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c @@ -137,7 +137,6 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu) /* Set the address of the incoming preemption record */ gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_LO, - REG_A5XX_CP_CONTEXT_SWITCH_RESTORE_ADDR_HI, a5xx_gpu->preempt_iova[ring->id]); a5xx_gpu->next_ring = ring; @@ -211,8 +210,7 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu) } /* Write a 0 to signal that we aren't switching pagetables */ - gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO, - REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_HI, 0); + gpu_write64(gpu, REG_A5XX_CP_CONTEXT_SWITCH_SMMU_INFO_LO, 0); /* Reset the preemption state */ set_preempt_state(a5xx_gpu, PREEMPT_NONE); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index fdc578016e0b..1ff605c18ee6 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -247,8 +247,7 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit) OUT_RING(ring, submit->seqno); trace_msm_gpu_submit_flush(submit, - gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, - REG_A6XX_CP_ALWAYS_ON_COUNTER_HI)); + gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO)); a6xx_flush(gpu, ring); } @@ -947,8 +946,7 @@ static int a6xx_ucode_init(struct msm_gpu *gpu) } } - gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE, - REG_A6XX_CP_SQE_INSTR_BASE+1, a6xx_gpu->sqe_iova); + gpu_write64(gpu, REG_A6XX_CP_SQE_INSTR_BASE, a6xx_gpu->sqe_iova); return 0; } @@ -999,8 +997,7 @@ static int hw_init(struct msm_gpu *gpu) * memory rendering at this point in time and we don't want to block off * part of the virtual memory space. */ - gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, - REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_HI, 0x00000000); + gpu_write64(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_BASE_LO, 0x00000000); gpu_write(gpu, REG_A6XX_RBBM_SECVID_TSB_TRUSTED_SIZE, 0x00000000); /* Turn on 64 bit addressing for all blocks */ @@ -1049,11 +1046,9 @@ static int hw_init(struct msm_gpu *gpu) if (!adreno_is_a650_family(adreno_gpu)) { /* Set the GMEM VA range [0x100000:0x100000 + gpu->gmem - 1] */ - gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO, - REG_A6XX_UCHE_GMEM_RANGE_MIN_HI, 0x00100000); + gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MIN_LO, 0x00100000); gpu_write64(gpu, REG_A6XX_UCHE_GMEM_RANGE_MAX_LO, - REG_A6XX_UCHE_GMEM_RANGE_MAX_HI, 0x00100000 + adreno_gpu->gmem - 1); } @@ -1145,8 +1140,7 @@ static int hw_init(struct msm_gpu *gpu) goto out; /* Set the ringbuffer address */ - gpu_write64(gpu, REG_A6XX_CP_RB_BASE, REG_A6XX_CP_RB_BASE_HI, - gpu->rb[0]->iova); + gpu_write64(gpu, REG_A6XX_CP_RB_BASE, gpu->rb[0]->iova); /* Targets that support extended APRIV can use the RPTR shadow from * hardware but all the other ones need to disable the feature. Targets @@ -1178,7 +1172,6 @@ static int hw_init(struct msm_gpu *gpu) } gpu_write64(gpu, REG_A6XX_CP_RB_RPTR_ADDR_LO, - REG_A6XX_CP_RB_RPTR_ADDR_HI, shadowptr(a6xx_gpu, gpu->rb[0])); } @@ -1499,9 +1492,9 @@ static void a6xx_fault_detect_irq(struct msm_gpu *gpu) gpu_read(gpu, REG_A6XX_RBBM_STATUS), gpu_read(gpu, REG_A6XX_CP_RB_RPTR), gpu_read(gpu, REG_A6XX_CP_RB_WPTR), - gpu_read64(gpu, REG_A6XX_CP_IB1_BASE, REG_A6XX_CP_IB1_BASE_HI), + gpu_read64(gpu, REG_A6XX_CP_IB1_BASE), gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE), - gpu_read64(gpu, REG_A6XX_CP_IB2_BASE, REG_A6XX_CP_IB2_BASE_HI), + gpu_read64(gpu, REG_A6XX_CP_IB2_BASE), gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE)); /* Turn off the hangcheck timer to keep it from bothering us */ @@ -1712,8 +1705,7 @@ static int a6xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value) /* Force the GPU power on so we can read this register */ a6xx_gmu_set_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); - *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO, - REG_A6XX_CP_ALWAYS_ON_COUNTER_HI); + *value = gpu_read64(gpu, REG_A6XX_CP_ALWAYS_ON_COUNTER_LO); a6xx_gmu_clear_oob(&a6xx_gpu->gmu, GMU_OOB_PERFCOUNTER_SET); diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c index a5c3d1ed255a..a023d5f962dc 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c @@ -147,8 +147,7 @@ static int a6xx_crashdumper_run(struct msm_gpu *gpu, /* Make sure all pending memory writes are posted */ wmb(); - gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO, - REG_A6XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova); + gpu_write64(gpu, REG_A6XX_CP_CRASH_SCRIPT_BASE_LO, dumper->iova); gpu_write(gpu, REG_A6XX_CP_CRASH_DUMP_CNTL, 1); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 58a72e6b1400..585fd9c8d45a 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -540,7 +540,7 @@ static inline void gpu_rmw(struct msm_gpu *gpu, u32 reg, u32 mask, u32 or) msm_rmw(gpu->mmio + (reg << 2), mask, or); } -static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi) +static inline u64 gpu_read64(struct msm_gpu *gpu, u32 reg) { u64 val; @@ -558,17 +558,17 @@ static inline u64 gpu_read64(struct msm_gpu *gpu, u32 lo, u32 hi) * when the lo is read, so make sure to read the lo first to trigger * that */ - val = (u64) msm_readl(gpu->mmio + (lo << 2)); - val |= ((u64) msm_readl(gpu->mmio + (hi << 2)) << 32); + val = (u64) msm_readl(gpu->mmio + (reg << 2)); + val |= ((u64) msm_readl(gpu->mmio + ((reg + 1) << 2)) << 32); return val; } -static inline void gpu_write64(struct msm_gpu *gpu, u32 lo, u32 hi, u64 val) +static inline void gpu_write64(struct msm_gpu *gpu, u32 reg, u64 val) { /* Why not a writeq here? Read the screed above */ - msm_writel(lower_32_bits(val), gpu->mmio + (lo << 2)); - msm_writel(upper_32_bits(val), gpu->mmio + (hi << 2)); + msm_writel(lower_32_bits(val), gpu->mmio + (reg << 2)); + msm_writel(upper_32_bits(val), gpu->mmio + ((reg + 1) << 2)); } int msm_gpu_pm_suspend(struct msm_gpu *gpu); From patchwork Fri Nov 4 15:08:39 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Rob Clark X-Patchwork-Id: 621794 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 1FCD7C4332F for ; Fri, 4 Nov 2022 15:08:41 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S232369AbiKDPIh (ORCPT ); Fri, 4 Nov 2022 11:08:37 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52826 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S232380AbiKDPIg (ORCPT ); Fri, 4 Nov 2022 11:08:36 -0400 Received: from mail-pf1-x42f.google.com (mail-pf1-x42f.google.com [IPv6:2607:f8b0:4864:20::42f]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id BAD272AEA; Fri, 4 Nov 2022 08:08:34 -0700 (PDT) Received: by mail-pf1-x42f.google.com with SMTP id k15so4772242pfg.2; Fri, 04 Nov 2022 08:08:34 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=Tubi0QTMdkad7hrgfgDxR0Y1fIIjP+8lDNHbALWluvQ=; b=E1K+1yvJ96nCX46BN7OqmZ39YeY19x/dxURzqGRdm7yLA9UV/Btcd7Aw0gQaVaCEfA IoiZ8x7Mh3qVlKGya6dgQf6jSUcF3t22CG3LV/zcf3v/i68Q7tJGo2sGhZHIu8MzXsV0 xoQmJ3yHRpz78tz5kRQPax/69FQKoIN26swG1fgL1oBwf16myV51weszGiI025THUgvU IrGRQuO8mIFX4ztTE4K99NGWVBJEyjf+ignLWrDnK2tDeEoA+f2l5mllt/PSGmqRQGg8 6gkIyjQpjkeq2qXCtrHtP4Rns0mtZJfZHR0xgTnHY/AN8+/sV9m8CVV7KX70PhXQJQvB Z4Gg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20210112; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=Tubi0QTMdkad7hrgfgDxR0Y1fIIjP+8lDNHbALWluvQ=; b=uOM2Rt/mkA0gpMZvwGvr0ho3Ymtm1lGbRtHMv2Sh7PXJyUO/EhZlDQD94W7uk5mcH7 QYX9bjZsDtYKAXTH5hUdN6LEZqAjLkeWDo9cMjMgB01Qly1VLzehznAkvQvG1qqFM1Sy g/MX4zPvJfXrKF3QrpNi1jrrmky1wpeZlw6x+QF/f3sBcRE6DAwqF4gvGHkdIMBpI40f t42ytNHDBbQZZu9VsLorjZXeZx/ot0dySfUArKjrqfg+NikiUifm5XAg5h4Y3Ad2cB/Q jyeJYgOZ8+WfmJPQFQa3OxHZ76/gX8/oJP5uFXvLKN1UYDCjM+XtbwOGsJChirkEa+QH /ZcA== X-Gm-Message-State: ACrzQf3+LQnlfWoLjBKj4BRaCQ5uTQgKjzKCcitj9J0qZF4EMIHhqmDv vlxWtG5GtTY3zkibzOdEZjQ= X-Google-Smtp-Source: AMsMyM5HTt387dIfF1j9FfL0KEi/eoKMuvBuZCGOQppTMU9k8VwOroeaq7sEpcMgkEJrK96hepX8yw== X-Received: by 2002:a65:4909:0:b0:46b:2752:e4ab with SMTP id p9-20020a654909000000b0046b2752e4abmr31370020pgs.293.1667574514122; Fri, 04 Nov 2022 08:08:34 -0700 (PDT) Received: from localhost ([2a00:79e1:abd:4a00:2703:3c72:eb1a:cffd]) by smtp.gmail.com with ESMTPSA id 123-20020a621781000000b00562784609fbsm2792890pfx.209.2022.11.04.08.08.33 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 04 Nov 2022 08:08:33 -0700 (PDT) From: Rob Clark To: dri-devel@lists.freedesktop.org Cc: freedreno@lists.freedesktop.org, linux-arm-msm@vger.kernel.org, Rob Clark , Akhil P Oommen , Rob Clark , Abhinav Kumar , Dmitry Baryshkov , Sean Paul , David Airlie , Daniel Vetter , Chia-I Wu , Konrad Dybcio , Douglas Anderson , linux-kernel@vger.kernel.org (open list) Subject: [PATCH v3 2/2] drm/msm: Hangcheck progress detection Date: Fri, 4 Nov 2022 08:08:39 -0700 Message-Id: <20221104150847.525173-3-robdclark@gmail.com> X-Mailer: git-send-email 2.38.1 In-Reply-To: <20221104150847.525173-1-robdclark@gmail.com> References: <20221104150847.525173-1-robdclark@gmail.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: linux-arm-msm@vger.kernel.org From: Rob Clark If the hangcheck timer expires, check if the fw's position in the cmdstream has advanced (changed) since last timer expiration, and allow it up to three additional "extensions" to it's alotted time. The intention is to continue to catch "shader stuck in a loop" type hangs quickly, but allow more time for things that are actually making forward progress. Because we need to sample the CP state twice to detect if there has not been progress, this also cuts the the timer's duration in half. v2: Fix typo (REG_A6XX_CP_CSQ_IB2_STAT), add comment v3: Only halve hangcheck timer duration for generations which support progress detection (hdanton); removed unused a5xx progress (without knowing how to adjust for data buffered in ROQ it is too likely to report a false negative) Signed-off-by: Rob Clark Reviewed-by: Akhil P Oommen Reviewed-by: Chia-I Wu Tested-by: Chia-I Wu --- drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 34 +++++++++++++++++++++++++++ drivers/gpu/drm/msm/msm_drv.c | 1 - drivers/gpu/drm/msm/msm_drv.h | 8 ++++++- drivers/gpu/drm/msm/msm_gpu.c | 31 +++++++++++++++++++++++- drivers/gpu/drm/msm/msm_gpu.h | 3 +++ drivers/gpu/drm/msm/msm_ringbuffer.h | 24 +++++++++++++++++++ 6 files changed, 98 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c index 1ff605c18ee6..7fe60c65a1eb 100644 --- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c @@ -1843,6 +1843,39 @@ static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring) return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR); } +static bool a6xx_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + struct msm_cp_state cp_state = { + .ib1_base = gpu_read64(gpu, REG_A6XX_CP_IB1_BASE), + .ib2_base = gpu_read64(gpu, REG_A6XX_CP_IB2_BASE), + .ib1_rem = gpu_read(gpu, REG_A6XX_CP_IB1_REM_SIZE), + .ib2_rem = gpu_read(gpu, REG_A6XX_CP_IB2_REM_SIZE), + }; + bool progress; + + /* + * Adjust the remaining data to account for what has already been + * fetched from memory, but not yet consumed by the SQE. + * + * This is not *technically* correct, the amount buffered could + * exceed the IB size due to hw prefetching ahead, but: + * + * (1) We aren't trying to find the exact position, just whether + * progress has been made + * (2) The CP_REG_TO_MEM at the end of a submit should be enough + * to prevent prefetching into an unrelated submit. (And + * either way, at some point the ROQ will be full.) + */ + cp_state.ib1_rem += gpu_read(gpu, REG_A6XX_CP_CSQ_IB1_STAT) >> 16; + cp_state.ib2_rem += gpu_read(gpu, REG_A6XX_CP_CSQ_IB2_STAT) >> 16; + + progress = !!memcmp(&cp_state, &ring->last_cp_state, sizeof(cp_state)); + + ring->last_cp_state = cp_state; + + return progress; +} + static u32 a618_get_speed_bin(u32 fuse) { if (fuse == 0) @@ -1961,6 +1994,7 @@ static const struct adreno_gpu_funcs funcs = { .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_get_timestamp, }; diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c index 670651cdfa79..c3b77b44b2aa 100644 --- a/drivers/gpu/drm/msm/msm_drv.c +++ b/drivers/gpu/drm/msm/msm_drv.c @@ -419,7 +419,6 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv) priv->dev = ddev; priv->wq = alloc_ordered_workqueue("msm", 0); - priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD; INIT_LIST_HEAD(&priv->objects); mutex_init(&priv->obj_lock); diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h index 0609daf4fa4c..876d8d5eec2f 100644 --- a/drivers/gpu/drm/msm/msm_drv.h +++ b/drivers/gpu/drm/msm/msm_drv.h @@ -225,7 +225,13 @@ struct msm_drm_private { struct drm_atomic_state *pm_state; - /* For hang detection, in ms */ + /** + * hangcheck_period: For hang detection, in ms + * + * Note that in practice, a submit/job will get at least two hangcheck + * periods, due to checking for progress being implemented as simply + * "have the CP position registers changed since last time?" + */ unsigned int hangcheck_period; /** diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c index 3dffee54a951..bfef659d3a5c 100644 --- a/drivers/gpu/drm/msm/msm_gpu.c +++ b/drivers/gpu/drm/msm/msm_gpu.c @@ -500,6 +500,21 @@ static void hangcheck_timer_reset(struct msm_gpu *gpu) round_jiffies_up(jiffies + msecs_to_jiffies(priv->hangcheck_period))); } +static bool made_progress(struct msm_gpu *gpu, struct msm_ringbuffer *ring) +{ + if (ring->hangcheck_progress_retries >= DRM_MSM_HANGCHECK_PROGRESS_RETRIES) + return false; + + if (!gpu->funcs->progress) + return false; + + if (!gpu->funcs->progress(gpu, ring)) + return false; + + ring->hangcheck_progress_retries++; + return true; +} + static void hangcheck_handler(struct timer_list *t) { struct msm_gpu *gpu = from_timer(gpu, t, hangcheck_timer); @@ -511,9 +526,12 @@ static void hangcheck_handler(struct timer_list *t) if (fence != ring->hangcheck_fence) { /* some progress has been made.. ya! */ ring->hangcheck_fence = fence; - } else if (fence_before(fence, ring->fctx->last_fence)) { + ring->hangcheck_progress_retries = 0; + } else if (fence_before(fence, ring->fctx->last_fence) && + !made_progress(gpu, ring)) { /* no progress and not done.. hung! */ ring->hangcheck_fence = fence; + ring->hangcheck_progress_retries = 0; DRM_DEV_ERROR(dev->dev, "%s: hangcheck detected gpu lockup rb %d!\n", gpu->name, ring->id); DRM_DEV_ERROR(dev->dev, "%s: completed fence: %u\n", @@ -845,6 +863,7 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, struct msm_gpu *gpu, const struct msm_gpu_funcs *funcs, const char *name, struct msm_gpu_config *config) { + struct msm_drm_private *priv = drm->dev_private; int i, ret, nr_rings = config->nr_rings; void *memptrs; uint64_t memptrs_iova; @@ -872,6 +891,16 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev, kthread_init_work(&gpu->recover_work, recover_worker); kthread_init_work(&gpu->fault_work, fault_worker); + priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD; + + /* + * If progress detection is supported, halve the hangcheck timer + * duration, as it takes two iterations of the hangcheck handler + * to detect a hang. + */ + if (funcs->progress) + priv->hangcheck_period /= 2; + timer_setup(&gpu->hangcheck_timer, hangcheck_handler, 0); spin_lock_init(&gpu->perf_lock); diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h index 585fd9c8d45a..f0fbf6063baa 100644 --- a/drivers/gpu/drm/msm/msm_gpu.h +++ b/drivers/gpu/drm/msm/msm_gpu.h @@ -78,6 +78,8 @@ struct msm_gpu_funcs { struct msm_gem_address_space *(*create_private_address_space) (struct msm_gpu *gpu); uint32_t (*get_rptr)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); + + bool (*progress)(struct msm_gpu *gpu, struct msm_ringbuffer *ring); }; /* Additional state for iommu faults: */ @@ -237,6 +239,7 @@ struct msm_gpu { #define DRM_MSM_INACTIVE_PERIOD 66 /* in ms (roughly four frames) */ #define DRM_MSM_HANGCHECK_DEFAULT_PERIOD 500 /* in ms */ +#define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3 struct timer_list hangcheck_timer; /* Fault info for most recent iova fault: */ diff --git a/drivers/gpu/drm/msm/msm_ringbuffer.h b/drivers/gpu/drm/msm/msm_ringbuffer.h index 2a5045abe46e..e3d33bae3380 100644 --- a/drivers/gpu/drm/msm/msm_ringbuffer.h +++ b/drivers/gpu/drm/msm/msm_ringbuffer.h @@ -35,6 +35,11 @@ struct msm_rbmemptrs { volatile u64 ttbr0; }; +struct msm_cp_state { + uint64_t ib1_base, ib2_base; + uint32_t ib1_rem, ib2_rem; +}; + struct msm_ringbuffer { struct msm_gpu *gpu; int id; @@ -64,6 +69,25 @@ struct msm_ringbuffer { uint64_t memptrs_iova; struct msm_fence_context *fctx; + /** + * hangcheck_progress_retries: + * + * The number of extra hangcheck duration cycles that we have given + * due to it appearing that the GPU is making forward progress. + * + * If the GPU appears to be making progress (ie. the CP has advanced + * in the command stream, we'll allow up to DRM_MSM_HANGCHECK_PROGRESS_RETRIES + * expirations of the hangcheck timer before killing the job. In other + * words we'll let the submit run for up to + * DRM_MSM_HANGCHECK_DEFAULT_PERIOD * DRM_MSM_HANGCHECK_PROGRESS_RETRIES + */ + int hangcheck_progress_retries; + + /** + * last_cp_state: The state of the CP at the last call to gpu->progress() + */ + struct msm_cp_state last_cp_state; + /* * preempt_lock protects preemption and serializes wptr updates against * preemption. Can be aquired from irq context.