Merge tag 'drm-msm-fixes-2023-07-27' of https://gitlab.freedesktop.org/drm/msm into drm-fixes

Fixes for v6.5-rc4

Display:
+ Fix to correct the UBWC programming for decoder version 4.3 seen
  on SM8550
+ Add the missing flush and fetch bits for DMA4 and DMA5 SSPPs.
+ Fix to drop the unused dpu_core_perf_data_bus_id enum from the code
+ Drop the unused dsi_phy_14nm_17mA_regulators from QCM 2290 DSI cfg.

GPU:
+ Fix warn splat for newer devices without revn
+ Remove name/revn for a690.. we shouldn't be populating these for
  newer devices, for consistency, but it slipped through review
+ Fix a6xx gpu snapshot BINDLESS_DATA size (was listed in bytes
  instead of dwords, causing AHB faults on a6xx gen4/a660-family)
+ Disallow submit with fence id 0
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGs9MwCSfiyv8i7yWAsJKYEzCDyzaTx=ujX80Y23rZd9RA@mail.gmail.com

drivers/gpu/drm/msm/adreno/a5xx_gpu.c

@@ -89,7 +89,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit
 			 * since we've already mapped it once in
 			 * submit_reloc()
 			 */
-			if (WARN_ON(!ptr))
+			if (WARN_ON(IS_ERR_OR_NULL(ptr)))
 				return;
 
 			for (i = 0; i < dwords; i++) {

drivers/gpu/drm/msm/adreno/a6xx_gpu_state.h

@@ -206,7 +206,7 @@ static const struct a6xx_shader_block {
 	SHADER(A6XX_SP_LB_3_DATA, 0x800),
 	SHADER(A6XX_SP_LB_4_DATA, 0x800),
 	SHADER(A6XX_SP_LB_5_DATA, 0x200),
-	SHADER(A6XX_SP_CB_BINDLESS_DATA, 0x2000),
+	SHADER(A6XX_SP_CB_BINDLESS_DATA, 0x800),
 	SHADER(A6XX_SP_CB_LEGACY_DATA, 0x280),
 	SHADER(A6XX_SP_UAV_DATA, 0x80),
 	SHADER(A6XX_SP_INST_TAG, 0x80),

drivers/gpu/drm/msm/adreno/adreno_device.c

@@ -369,8 +369,6 @@ static const struct adreno_info gpulist[] = {
 		.hwcg = a640_hwcg,
 	}, {
 		.rev = ADRENO_REV(6, 9, 0, ANY_ID),
-		.revn = 690,
-		.name = "A690",
 		.fw = {
 			[ADRENO_FW_SQE] = "a660_sqe.fw",
 			[ADRENO_FW_GMU] = "a690_gmu.bin",

drivers/gpu/drm/msm/adreno/adreno_gpu.h

@@ -149,7 +149,8 @@ bool adreno_cmp_rev(struct adreno_rev rev1, struct adreno_rev rev2);
 
 static inline bool adreno_is_revn(const struct adreno_gpu *gpu, uint32_t revn)
 {
-	WARN_ON_ONCE(!gpu->revn);
+	/* revn can be zero, but if not is set at same time as info */
+	WARN_ON_ONCE(!gpu->info);
 
 	return gpu->revn == revn;
 }
@@ -161,14 +162,16 @@ static inline bool adreno_has_gmu_wrapper(const struct adreno_gpu *gpu)
 
 static inline bool adreno_is_a2xx(const struct adreno_gpu *gpu)
 {
-	WARN_ON_ONCE(!gpu->revn);
+	/* revn can be zero, but if not is set at same time as info */
+	WARN_ON_ONCE(!gpu->info);
 
 	return (gpu->revn < 300);
 }
 
 static inline bool adreno_is_a20x(const struct adreno_gpu *gpu)
 {
-	WARN_ON_ONCE(!gpu->revn);
+	/* revn can be zero, but if not is set at same time as info */
+	WARN_ON_ONCE(!gpu->info);
 
 	return (gpu->revn < 210);
 }
@@ -307,7 +310,8 @@ static inline int adreno_is_a680(const struct adreno_gpu *gpu)
 
 static inline int adreno_is_a690(const struct adreno_gpu *gpu)
 {
-	return adreno_is_revn(gpu, 690);
+	/* The order of args is important here to handle ANY_ID correctly */
+	return adreno_cmp_rev(ADRENO_REV(6, 9, 0, ANY_ID), gpu->rev);
 };
 
 /* check for a615, a616, a618, a619 or any derivatives */

drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h

@@ -14,19 +14,6 @@
 
 #define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
 
-/**
- * enum dpu_core_perf_data_bus_id - data bus identifier
- * @DPU_CORE_PERF_DATA_BUS_ID_MNOC: DPU/MNOC data bus
- * @DPU_CORE_PERF_DATA_BUS_ID_LLCC: MNOC/LLCC data bus
- * @DPU_CORE_PERF_DATA_BUS_ID_EBI: LLCC/EBI data bus
- */
-enum dpu_core_perf_data_bus_id {
-	DPU_CORE_PERF_DATA_BUS_ID_MNOC,
-	DPU_CORE_PERF_DATA_BUS_ID_LLCC,
-	DPU_CORE_PERF_DATA_BUS_ID_EBI,
-	DPU_CORE_PERF_DATA_BUS_ID_MAX,
-};
-
 /**
  * struct dpu_core_perf_params - definition of performance parameters
  * @max_per_pipe_ib: maximum instantaneous bandwidth request

drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c

@@ -51,7 +51,7 @@
 
 static const u32 fetch_tbl[SSPP_MAX] = {CTL_INVALID_BIT, 16, 17, 18, 19,
 	CTL_INVALID_BIT, CTL_INVALID_BIT, CTL_INVALID_BIT, CTL_INVALID_BIT, 0,
-	1, 2, 3, CTL_INVALID_BIT, CTL_INVALID_BIT};
+	1, 2, 3, 4, 5};
 
 static int _mixer_stages(const struct dpu_lm_cfg *mixer, int count,
 		enum dpu_lm lm)
@@ -198,6 +198,12 @@ static void dpu_hw_ctl_update_pending_flush_sspp(struct dpu_hw_ctl *ctx,
 	case SSPP_DMA3:
 		ctx->pending_flush_mask |= BIT(25);
 		break;
+	case SSPP_DMA4:
+		ctx->pending_flush_mask |= BIT(13);
+		break;
+	case SSPP_DMA5:
+		ctx->pending_flush_mask |= BIT(14);
+		break;
 	case SSPP_CURSOR0:
 		ctx->pending_flush_mask |= BIT(22);
 		break;

drivers/gpu/drm/msm/dsi/phy/dsi_phy_14nm.c

@@ -1087,8 +1087,6 @@ const struct msm_dsi_phy_cfg dsi_phy_14nm_8953_cfgs = {
 
 const struct msm_dsi_phy_cfg dsi_phy_14nm_2290_cfgs = {
 	.has_phy_lane = true,
-	.regulator_data = dsi_phy_14nm_17mA_regulators,
-	.num_regulators = ARRAY_SIZE(dsi_phy_14nm_17mA_regulators),
 	.ops = {
 		.enable = dsi_14nm_phy_enable,
 		.disable = dsi_14nm_phy_disable,

drivers/gpu/drm/msm/msm_fence.c

@@ -191,6 +191,12 @@ msm_fence_init(struct dma_fence *fence, struct msm_fence_context *fctx)
 
 	f->fctx = fctx;
 
+	/*
+	 * Until this point, the fence was just some pre-allocated memory,
+	 * no-one should have taken a reference to it yet.
+	 */
+	WARN_ON(kref_read(&fence->refcount));
+
 	dma_fence_init(&f->base, &msm_fence_ops, &fctx->spinlock,
 		       fctx->context, ++fctx->last_fence);
 }

drivers/gpu/drm/msm/msm_gem_submit.c

@@ -86,7 +86,19 @@ void __msm_gem_submit_destroy(struct kref *kref)
 	}
 
 	dma_fence_put(submit->user_fence);
-	dma_fence_put(submit->hw_fence);
+
+	/*
+	 * If the submit is freed before msm_job_run(), then hw_fence is
+	 * just some pre-allocated memory, not a reference counted fence.
+	 * Once the job runs and the hw_fence is initialized, it will
+	 * have a refcount of at least one, since the submit holds a ref
+	 * to the hw_fence.
+	 */
+	if (kref_read(&submit->hw_fence->refcount) == 0) {
+		kfree(submit->hw_fence);
+	} else {
+		dma_fence_put(submit->hw_fence);
+	}
 
 	put_pid(submit->pid);
 	msm_submitqueue_put(submit->queue);
@@ -889,7 +901,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	 * after the job is armed
 	 */
 	if ((args->flags & MSM_SUBMIT_FENCE_SN_IN) &&
-			idr_find(&queue->fence_idr, args->fence)) {
+			(!args->fence || idr_find(&queue->fence_idr, args->fence))) {
 		spin_unlock(&queue->idr_lock);
 		idr_preload_end();
 		ret = -EINVAL;

drivers/gpu/drm/msm/msm_mdss.c

@@ -189,6 +189,7 @@ static int _msm_mdss_irq_domain_add(struct msm_mdss *msm_mdss)
 #define UBWC_2_0 0x20000000
 #define UBWC_3_0 0x30000000
 #define UBWC_4_0 0x40000000
+#define UBWC_4_3 0x40030000
 
 static void msm_mdss_setup_ubwc_dec_20(struct msm_mdss *msm_mdss)
 {
@@ -227,7 +228,10 @@ static void msm_mdss_setup_ubwc_dec_40(struct msm_mdss *msm_mdss)
 		writel_relaxed(1, msm_mdss->mmio + UBWC_CTRL_2);
 		writel_relaxed(0, msm_mdss->mmio + UBWC_PREDICTION_MODE);
 	} else {
-		writel_relaxed(2, msm_mdss->mmio + UBWC_CTRL_2);
+		if (data->ubwc_dec_version == UBWC_4_3)
+			writel_relaxed(3, msm_mdss->mmio + UBWC_CTRL_2);
+		else
+			writel_relaxed(2, msm_mdss->mmio + UBWC_CTRL_2);
 		writel_relaxed(1, msm_mdss->mmio + UBWC_PREDICTION_MODE);
 	}
 }
@@ -271,6 +275,7 @@ static int msm_mdss_enable(struct msm_mdss *msm_mdss)
 		msm_mdss_setup_ubwc_dec_30(msm_mdss);
 		break;
 	case UBWC_4_0:
+	case UBWC_4_3:
 		msm_mdss_setup_ubwc_dec_40(msm_mdss);
 		break;
 	default:
@@ -569,6 +574,16 @@ static const struct msm_mdss_data sm8250_data = {
 	.macrotile_mode = 1,
 };
 
+static const struct msm_mdss_data sm8550_data = {
+	.ubwc_version = UBWC_4_0,
+	.ubwc_dec_version = UBWC_4_3,
+	.ubwc_swizzle = 6,
+	.ubwc_static = 1,
+	/* TODO: highest_bank_bit = 2 for LP_DDR4 */
+	.highest_bank_bit = 3,
+	.macrotile_mode = 1,
+};
+
 static const struct of_device_id mdss_dt_match[] = {
 	{ .compatible = "qcom,mdss" },
 	{ .compatible = "qcom,msm8998-mdss" },
@@ -585,7 +600,7 @@ static const struct of_device_id mdss_dt_match[] = {
 	{ .compatible = "qcom,sm8250-mdss", .data = &sm8250_data },
 	{ .compatible = "qcom,sm8350-mdss", .data = &sm8250_data },
 	{ .compatible = "qcom,sm8450-mdss", .data = &sm8250_data },
-	{ .compatible = "qcom,sm8550-mdss", .data = &sm8250_data },
+	{ .compatible = "qcom,sm8550-mdss", .data = &sm8550_data },
 	{}
 };
 MODULE_DEVICE_TABLE(of, mdss_dt_match);