Merge tag 'drm-msm-fixes-2025-06-16' of https://gitlab.freedesktop.org/drm/msm into drm-fixes

Fixes for v6.16-rc3

Display:
- Fixed DP output on SDM845
- Fixed 10nm DSI PLL init

GPU:
- SUBMIT ioctl error path leak fixes
- drm half of stall-on-fault fixes.  Note there is a soft dependency,
  to get correct mmu fault devcoredumps, on arm-smmu changes which
  are not in this branch, but have already been merged by Linus.  So
  by the time Linus merges this, everything should be peachy.
- a7xx: Missing CP_RESET_CONTEXT_STATE
- Skip GPU component bind if GPU is not in the device table.

Signed-off-by: Dave Airlie <[email protected]>
From: Rob Clark <[email protected]>
Link: https://lore.kernel.org/r/CACSVV03=OH74ip8O1xqb8RJWGyM4HFuUnWuR=p3zJR+-ko_AJA@mail.gmail.com

Author: airlied

drivers/gpu/drm/msm/adreno/a2xx_gpummu.c

@@ -71,10 +71,6 @@ static int a2xx_gpummu_unmap(struct msm_mmu *mmu, uint64_t iova, size_t len)
 	return 0;
 }
 
-static void a2xx_gpummu_resume_translation(struct msm_mmu *mmu)
-{
-}
-
 static void a2xx_gpummu_destroy(struct msm_mmu *mmu)
 {
 	struct a2xx_gpummu *gpummu = to_a2xx_gpummu(mmu);
@@ -90,7 +86,6 @@ static const struct msm_mmu_funcs funcs = {
 		.map = a2xx_gpummu_map,
 		.unmap = a2xx_gpummu_unmap,
 		.destroy = a2xx_gpummu_destroy,
-		.resume_translation = a2xx_gpummu_resume_translation,
 };
 
 struct msm_mmu *a2xx_gpummu_new(struct device *dev, struct msm_gpu *gpu)

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

@@ -131,6 +131,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i, ibs = 0;
 
+	adreno_check_and_reenable_stall(adreno_gpu);
+
 	if (IS_ENABLED(CONFIG_DRM_MSM_GPU_SUDO) && submit->in_rb) {
 		ring->cur_ctx_seqno = 0;
 		a5xx_submit_in_rb(gpu, submit);

drivers/gpu/drm/msm/adreno/a6xx_gpu.c

@@ -130,6 +130,20 @@ static void a6xx_set_pagetable(struct a6xx_gpu *a6xx_gpu,
 		OUT_RING(ring, lower_32_bits(rbmemptr(ring, fence)));
 		OUT_RING(ring, upper_32_bits(rbmemptr(ring, fence)));
 		OUT_RING(ring, submit->seqno - 1);
+
+		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+		OUT_RING(ring, CP_SET_THREAD_BOTH);
+
+		/* Reset state used to synchronize BR and BV */
+		OUT_PKT7(ring, CP_RESET_CONTEXT_STATE, 1);
+		OUT_RING(ring,
+			 CP_RESET_CONTEXT_STATE_0_CLEAR_ON_CHIP_TS |
+			 CP_RESET_CONTEXT_STATE_0_CLEAR_RESOURCE_TABLE |
+			 CP_RESET_CONTEXT_STATE_0_CLEAR_BV_BR_COUNTER |
+			 CP_RESET_CONTEXT_STATE_0_RESET_GLOBAL_LOCAL_TS);
+
+		OUT_PKT7(ring, CP_THREAD_CONTROL, 1);
+		OUT_RING(ring, CP_SET_THREAD_BR);
 	}
 
 	if (!sysprof) {
@@ -212,6 +226,8 @@ static void a6xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i, ibs = 0;
 
+	adreno_check_and_reenable_stall(adreno_gpu);
+
 	a6xx_set_pagetable(a6xx_gpu, ring, submit);
 
 	get_stats_counter(ring, REG_A6XX_RBBM_PERFCTR_CP(0),
@@ -335,6 +351,8 @@ static void a7xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	struct msm_ringbuffer *ring = submit->ring;
 	unsigned int i, ibs = 0;
 
+	adreno_check_and_reenable_stall(adreno_gpu);
+
 	/*
 	 * Toggle concurrent binning for pagetable switch and set the thread to
 	 * BR since only it can execute the pagetable switch packets.

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

@@ -137,9 +137,8 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 	return NULL;
 }
 
-static int find_chipid(struct device *dev, uint32_t *chipid)
+static int find_chipid(struct device_node *node, uint32_t *chipid)
 {
-	struct device_node *node = dev->of_node;
 	const char *compat;
 	int ret;
 
@@ -173,15 +172,36 @@ static int find_chipid(struct device *dev, uint32_t *chipid)
 	/* and if that fails, fall back to legacy "qcom,chipid" property: */
 	ret = of_property_read_u32(node, "qcom,chipid", chipid);
 	if (ret) {
-		DRM_DEV_ERROR(dev, "could not parse qcom,chipid: %d\n", ret);
+		DRM_ERROR("%pOF: could not parse qcom,chipid: %d\n",
+			  node, ret);
 		return ret;
 	}
 
-	dev_warn(dev, "Using legacy qcom,chipid binding!\n");
+	pr_warn("%pOF: Using legacy qcom,chipid binding!\n", node);
 
 	return 0;
 }
 
+bool adreno_has_gpu(struct device_node *node)
+{
+	const struct adreno_info *info;
+	uint32_t chip_id;
+	int ret;
+
+	ret = find_chipid(node, &chip_id);
+	if (ret)
+		return false;
+
+	info = adreno_info(chip_id);
+	if (!info) {
+		pr_warn("%pOF: Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n",
+			node, ADRENO_CHIPID_ARGS(chip_id));
+		return false;
+	}
+
+	return true;
+}
+
 static int adreno_bind(struct device *dev, struct device *master, void *data)
 {
 	static struct adreno_platform_config config = {};
@@ -191,19 +211,18 @@ static int adreno_bind(struct device *dev, struct device *master, void *data)
 	struct msm_gpu *gpu;
 	int ret;
 
-	ret = find_chipid(dev, &config.chip_id);
-	if (ret)
+	ret = find_chipid(dev->of_node, &config.chip_id);
+	/* We shouldn't have gotten this far if we can't parse the chip_id */
+	if (WARN_ON(ret))
 		return ret;
 
 	dev->platform_data = &config;
 	priv->gpu_pdev = to_platform_device(dev);
 
 	info = adreno_info(config.chip_id);
-	if (!info) {
-		dev_warn(drm->dev, "Unknown GPU revision: %"ADRENO_CHIPID_FMT"\n",
-			ADRENO_CHIPID_ARGS(config.chip_id));
+	/* We shouldn't have gotten this far if we don't recognize the GPU: */
+	if (WARN_ON(!info))
 		return -ENXIO;
-	}
 
 	config.info = info;
 

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

@@ -259,24 +259,54 @@ u64 adreno_private_address_space_size(struct msm_gpu *gpu)
 	return BIT(ttbr1_cfg->ias) - ADRENO_VM_START;
 }
 
+void adreno_check_and_reenable_stall(struct adreno_gpu *adreno_gpu)
+{
+	struct msm_gpu *gpu = &adreno_gpu->base;
+	struct msm_drm_private *priv = gpu->dev->dev_private;
+	unsigned long flags;
+
+	/*
+	 * Wait until the cooldown period has passed and we would actually
+	 * collect a crashdump to re-enable stall-on-fault.
+	 */
+	spin_lock_irqsave(&priv->fault_stall_lock, flags);
+	if (!priv->stall_enabled &&
+			ktime_after(ktime_get(), priv->stall_reenable_time) &&
+			!READ_ONCE(gpu->crashstate)) {
+		priv->stall_enabled = true;
+
+		gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, true);
+	}
+	spin_unlock_irqrestore(&priv->fault_stall_lock, flags);
+}
+
 #define ARM_SMMU_FSR_TF                 BIT(1)
 #define ARM_SMMU_FSR_PF			BIT(3)
 #define ARM_SMMU_FSR_EF			BIT(4)
+#define ARM_SMMU_FSR_SS			BIT(30)
 
 int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 			 struct adreno_smmu_fault_info *info, const char *block,
 			 u32 scratch[4])
 {
+	struct msm_drm_private *priv = gpu->dev->dev_private;
 	const char *type = "UNKNOWN";
-	bool do_devcoredump = info && !READ_ONCE(gpu->crashstate);
+	bool do_devcoredump = info && (info->fsr & ARM_SMMU_FSR_SS) &&
+		!READ_ONCE(gpu->crashstate);
+	unsigned long irq_flags;
 
 	/*
-	 * If we aren't going to be resuming later from fault_worker, then do
-	 * it now.
+	 * In case there is a subsequent storm of pagefaults, disable
+	 * stall-on-fault for at least half a second.
 	 */
-	if (!do_devcoredump) {
-		gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
+	spin_lock_irqsave(&priv->fault_stall_lock, irq_flags);
+	if (priv->stall_enabled) {
+		priv->stall_enabled = false;
+
+		gpu->aspace->mmu->funcs->set_stall(gpu->aspace->mmu, false);
 	}
+	priv->stall_reenable_time = ktime_add_ms(ktime_get(), 500);
+	spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags);
 
 	/*
 	 * Print a default message if we couldn't get the data from the
@@ -304,16 +334,18 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 			scratch[0], scratch[1], scratch[2], scratch[3]);
 
 	if (do_devcoredump) {
+		struct msm_gpu_fault_info fault_info = {};
+
 		/* Turn off the hangcheck timer to keep it from bothering us */
 		timer_delete(&gpu->hangcheck_timer);
 
-		gpu->fault_info.ttbr0 = info->ttbr0;
-		gpu->fault_info.iova  = iova;
-		gpu->fault_info.flags = flags;
-		gpu->fault_info.type  = type;
-		gpu->fault_info.block = block;
+		fault_info.ttbr0 = info->ttbr0;
+		fault_info.iova  = iova;
+		fault_info.flags = flags;
+		fault_info.type  = type;
+		fault_info.block = block;
 
-		kthread_queue_work(gpu->worker, &gpu->fault_work);
+		msm_gpu_fault_crashstate_capture(gpu, &fault_info);
 	}
 
 	return 0;

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

@@ -636,6 +636,8 @@ int adreno_fault_handler(struct msm_gpu *gpu, unsigned long iova, int flags,
 			 struct adreno_smmu_fault_info *info, const char *block,
 			 u32 scratch[4]);
 
+void adreno_check_and_reenable_stall(struct adreno_gpu *gpu);
+
 int adreno_read_speedbin(struct device *dev, u32 *speedbin);
 
 /*

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

@@ -94,17 +94,21 @@ static void drm_mode_to_intf_timing_params(
 		timing->vsync_polarity = 0;
 	}
 
-	/* for DP/EDP, Shift timings to align it to bottom right */
-	if (phys_enc->hw_intf->cap->type == INTF_DP) {
+	timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
+	timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent);
+
+	/*
+	 *  For DP/EDP, Shift timings to align it to bottom right.
+	 *  wide_bus_en is set for everything excluding SDM845 &
+	 *  porch changes cause DisplayPort failure and HDMI tearing.
+	 */
+	if (phys_enc->hw_intf->cap->type == INTF_DP && timing->wide_bus_en) {
 		timing->h_back_porch += timing->h_front_porch;
 		timing->h_front_porch = 0;
 		timing->v_back_porch += timing->v_front_porch;
 		timing->v_front_porch = 0;
 	}
 
-	timing->wide_bus_en = dpu_encoder_is_widebus_enabled(phys_enc->parent);
-	timing->compression_en = dpu_encoder_is_dsc_enabled(phys_enc->parent);
-
 	/*
 	 * for DP, divide the horizonal parameters by 2 when
 	 * widebus is enabled

drivers/gpu/drm/msm/dp/dp_display.c

@@ -128,6 +128,11 @@ static const struct msm_dp_desc msm_dp_desc_sa8775p[] = {
 	{}
 };
 
+static const struct msm_dp_desc msm_dp_desc_sdm845[] = {
+	{ .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0 },
+	{}
+};
+
 static const struct msm_dp_desc msm_dp_desc_sc7180[] = {
 	{ .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true },
 	{}
@@ -180,7 +185,7 @@ static const struct of_device_id msm_dp_dt_match[] = {
 	{ .compatible = "qcom,sc8180x-edp", .data = &msm_dp_desc_sc8180x },
 	{ .compatible = "qcom,sc8280xp-dp", .data = &msm_dp_desc_sc8280xp },
 	{ .compatible = "qcom,sc8280xp-edp", .data = &msm_dp_desc_sc8280xp },
-	{ .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sc7180 },
+	{ .compatible = "qcom,sdm845-dp", .data = &msm_dp_desc_sdm845 },
 	{ .compatible = "qcom,sm8350-dp", .data = &msm_dp_desc_sc7180 },
 	{ .compatible = "qcom,sm8650-dp", .data = &msm_dp_desc_sm8650 },
 	{ .compatible = "qcom,x1e80100-dp", .data = &msm_dp_desc_x1e80100 },

drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c

@@ -704,6 +704,13 @@ static int dsi_pll_10nm_init(struct msm_dsi_phy *phy)
 	/* TODO: Remove this when we have proper display handover support */
 	msm_dsi_phy_pll_save_state(phy);
 
+	/*
+	 * Store also proper vco_current_rate, because its value will be used in
+	 * dsi_10nm_pll_restore_state().
+	 */
+	if (!dsi_pll_10nm_vco_recalc_rate(&pll_10nm->clk_hw, VCO_REF_CLK_RATE))
+		pll_10nm->vco_current_rate = pll_10nm->phy->cfg->min_pll_rate;
+
 	return 0;
 }
 

drivers/gpu/drm/msm/msm_debugfs.c

@@ -208,6 +208,35 @@ DEFINE_DEBUGFS_ATTRIBUTE(shrink_fops,
 			 shrink_get, shrink_set,
 			 "0x%08llx\n");
 
+/*
+ * Return the number of microseconds to wait until stall-on-fault is
+ * re-enabled. If 0 then it is already enabled or will be re-enabled on the
+ * next submit (unless there's a leftover devcoredump). This is useful for
+ * kernel tests that intentionally produce a fault and check the devcoredump to
+ * wait until the cooldown period is over.
+ */
+
+static int
+stall_reenable_time_get(void *data, u64 *val)
+{
+	struct msm_drm_private *priv = data;
+	unsigned long irq_flags;
+
+	spin_lock_irqsave(&priv->fault_stall_lock, irq_flags);
+
+	if (priv->stall_enabled)
+		*val = 0;
+	else
+		*val = max(ktime_us_delta(priv->stall_reenable_time, ktime_get()), 0);
+
+	spin_unlock_irqrestore(&priv->fault_stall_lock, irq_flags);
+
+	return 0;
+}
+
+DEFINE_DEBUGFS_ATTRIBUTE(stall_reenable_time_fops,
+			 stall_reenable_time_get, NULL,
+			 "%lld\n");
 
 static int msm_gem_show(struct seq_file *m, void *arg)
 {
@@ -319,6 +348,9 @@ static void msm_debugfs_gpu_init(struct drm_minor *minor)
 	debugfs_create_bool("disable_err_irq", 0600, minor->debugfs_root,
 		&priv->disable_err_irq);
 
+	debugfs_create_file("stall_reenable_time_us", 0400, minor->debugfs_root,
+		priv, &stall_reenable_time_fops);
+
 	gpu_devfreq = debugfs_create_dir("devfreq", minor->debugfs_root);
 
 	debugfs_create_bool("idle_clamp",0600, gpu_devfreq,