19 files changed, 217 insertions, 67 deletions

diff --git a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c b/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
index 39641551eeb6..4280f71e472a 100644
--- a/drivers/gpu/drm/msm/adreno/a2xx_gpummu.c
+++ b/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)
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 650e5bac225f..60aef0796236 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/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);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index bf3758f010f4..491fde0083a2 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/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.
diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index f5e1490d07c1..16e7ac444efd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -137,9 +137,8 @@ err_disable_rpm:
 	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;
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 2348ffb35f7e..86bff915c3e7 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/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;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index a8f4bf416e64..bc063594a359 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/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);
 
 /*
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
index 8a618841e3ea..1c468ca5d692 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+++ b/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
diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index 386c4669c831..a48e6db4f156 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/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 },
diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
index 9812b4d69197..af2e30f3f842 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_10nm.c
+++ b/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;
 }
 
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 7ab607252d18..6af72162cda4 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/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,
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index f316e6776f67..d007687c2446 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -245,6 +245,10 @@ static int msm_drm_init(struct device *dev, const struct drm_driver *drv)
 	drm_gem_lru_init(&priv->lru.willneed, &priv->lru.lock);
 	drm_gem_lru_init(&priv->lru.dontneed, &priv->lru.lock);
 
+	/* Initialize stall-on-fault */
+	spin_lock_init(&priv->fault_stall_lock);
+	priv->stall_enabled = true;
+
 	/* Teach lockdep about lock ordering wrt. shrinker: */
 	fs_reclaim_acquire(GFP_KERNEL);
 	might_lock(&priv->lru.lock);
@@ -926,7 +930,7 @@ static const struct drm_driver msm_driver = {
  * is no external component that we need to add since LVDS is within MDP4
  * itself.
  */
-static int add_components_mdp(struct device *master_dev,
+static int add_mdp_components(struct device *master_dev,
 			      struct component_match **matchptr)
 {
 	struct device_node *np = master_dev->of_node;
@@ -1030,7 +1034,7 @@ static int add_gpu_components(struct device *dev,
 	if (!np)
 		return 0;
 
-	if (of_device_is_available(np))
+	if (of_device_is_available(np) && adreno_has_gpu(np))
 		drm_of_component_match_add(dev, matchptr, component_compare_of, np);
 
 	of_node_put(np);
@@ -1071,7 +1075,7 @@ int msm_drv_probe(struct device *master_dev,
 
 	/* Add mdp components if we have KMS. */
 	if (kms_init) {
-		ret = add_components_mdp(master_dev, &match);
+		ret = add_mdp_components(master_dev, &match);
 		if (ret)
 			return ret;
 	}
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index a65077855201..c8afb1ea6040 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -222,6 +222,29 @@ struct msm_drm_private {
 	 * the sw hangcheck mechanism.
 	 */
 	bool disable_err_irq;
+
+	/**
+	 * @fault_stall_lock:
+	 *
+	 * Serialize changes to stall-on-fault state.
+	 */
+	spinlock_t fault_stall_lock;
+
+	/**
+	 * @fault_stall_reenable_time:
+	 *
+	 * If stall_enabled is false, when to reenable stall-on-fault.
+	 * Protected by @fault_stall_lock.
+	 */
+	ktime_t stall_reenable_time;
+
+	/**
+	 * @stall_enabled:
+	 *
+	 * Whether stall-on-fault is currently enabled. Protected by
+	 * @fault_stall_lock.
+	 */
+	bool stall_enabled;
 };
 
 const struct msm_format *mdp_get_format(struct msm_kms *kms, uint32_t format, uint64_t modifier);
diff --git a/drivers/gpu/drm/msm/msm_gem_submit.c b/drivers/gpu/drm/msm/msm_gem_submit.c
index 3e9aa2cc38ef..d4f71bb54e84 100644
--- a/drivers/gpu/drm/msm/msm_gem_submit.c
+++ b/drivers/gpu/drm/msm/msm_gem_submit.c
@@ -85,6 +85,15 @@ void __msm_gem_submit_destroy(struct kref *kref)
 			container_of(kref, struct msm_gem_submit, ref);
 	unsigned i;
 
+	/*
+	 * In error paths, we could unref the submit without calling
+	 * drm_sched_entity_push_job(), so msm_job_free() will never
+	 * get called.  Since drm_sched_job_cleanup() will NULL out
+	 * s_fence, we can use that to detect this case.
+	 */
+	if (submit->base.s_fence)
+		drm_sched_job_cleanup(&submit->base);
+
 	if (submit->fence_id) {
 		spin_lock(&submit->queue->idr_lock);
 		idr_remove(&submit->queue->fence_idr, submit->fence_id);
@@ -649,6 +658,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	struct msm_ringbuffer *ring;
 	struct msm_submit_post_dep *post_deps = NULL;
 	struct drm_syncobj **syncobjs_to_reset = NULL;
+	struct sync_file *sync_file = NULL;
 	int out_fence_fd = -1;
 	unsigned i;
 	int ret;
@@ -858,7 +868,7 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	}
 
 	if (ret == 0 && args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
-		struct sync_file *sync_file = sync_file_create(submit->user_fence);
+		sync_file = sync_file_create(submit->user_fence);
 		if (!sync_file) {
 			ret = -ENOMEM;
 		} else {
@@ -892,8 +902,11 @@ out:
 out_unlock:
 	mutex_unlock(&queue->lock);
 out_post_unlock:
-	if (ret && (out_fence_fd >= 0))
+	if (ret && (out_fence_fd >= 0)) {
 		put_unused_fd(out_fence_fd);
+		if (sync_file)
+			fput(sync_file->file);
+	}
 
 	if (!IS_ERR_OR_NULL(submit)) {
 		msm_gem_submit_put(submit);
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 197871fdf508..3947f7ba1421 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -257,7 +257,8 @@ out:
 }
 
 static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
-		struct msm_gem_submit *submit, char *comm, char *cmd)
+		struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info,
+		char *comm, char *cmd)
 {
 	struct msm_gpu_state *state;
 
@@ -276,7 +277,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 	/* Fill in the additional crash state information */
 	state->comm = kstrdup(comm, GFP_KERNEL);
 	state->cmd = kstrdup(cmd, GFP_KERNEL);
-	state->fault_info = gpu->fault_info;
+	if (fault_info)
+		state->fault_info = *fault_info;
 
 	if (submit) {
 		int i;
@@ -308,7 +310,8 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
 }
 #else
 static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
-		struct msm_gem_submit *submit, char *comm, char *cmd)
+		struct msm_gem_submit *submit, struct msm_gpu_fault_info *fault_info,
+		char *comm, char *cmd)
 {
 }
 #endif
@@ -405,7 +408,7 @@ static void recover_worker(struct kthread_work *work)
 
 	/* Record the crash state */
 	pm_runtime_get_sync(&gpu->pdev->dev);
-	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+	msm_gpu_crashstate_capture(gpu, submit, NULL, comm, cmd);
 
 	kfree(cmd);
 	kfree(comm);
@@ -459,9 +462,8 @@ out_unlock:
 	msm_gpu_retire(gpu);
 }
 
-static void fault_worker(struct kthread_work *work)
+void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info)
 {
-	struct msm_gpu *gpu = container_of(work, struct msm_gpu, fault_work);
 	struct msm_gem_submit *submit;
 	struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
 	char *comm = NULL, *cmd = NULL;
@@ -484,16 +486,13 @@ static void fault_worker(struct kthread_work *work)
 
 	/* Record the crash state */
 	pm_runtime_get_sync(&gpu->pdev->dev);
-	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
+	msm_gpu_crashstate_capture(gpu, submit, fault_info, comm, cmd);
 	pm_runtime_put_sync(&gpu->pdev->dev);
 
 	kfree(cmd);
 	kfree(comm);
 
 resume_smmu:
-	memset(&gpu->fault_info, 0, sizeof(gpu->fault_info));
-	gpu->aspace->mmu->funcs->resume_translation(gpu->aspace->mmu);
-
 	mutex_unlock(&gpu->lock);
 }
 
@@ -882,7 +881,6 @@ int msm_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 	init_waitqueue_head(&gpu->retire_event);
 	kthread_init_work(&gpu->retire_work, retire_worker);
 	kthread_init_work(&gpu->recover_work, recover_worker);
-	kthread_init_work(&gpu->fault_work, fault_worker);
 
 	priv->hangcheck_period = DRM_MSM_HANGCHECK_DEFAULT_PERIOD;
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index e25009150579..5bf7cd985b9c 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -253,12 +253,6 @@ struct msm_gpu {
 #define DRM_MSM_HANGCHECK_PROGRESS_RETRIES 3
 	struct timer_list hangcheck_timer;
 
-	/* Fault info for most recent iova fault: */
-	struct msm_gpu_fault_info fault_info;
-
-	/* work for handling GPU ioval faults: */
-	struct kthread_work fault_work;
-
 	/* work for handling GPU recovery: */
 	struct kthread_work recover_work;
 
@@ -668,6 +662,7 @@ msm_gpu_create_private_address_space(struct msm_gpu *gpu, struct task_struct *ta
 void msm_gpu_cleanup(struct msm_gpu *gpu);
 
 struct msm_gpu *adreno_load_gpu(struct drm_device *dev);
+bool adreno_has_gpu(struct device_node *node);
 void __init adreno_register(void);
 void __exit adreno_unregister(void);
 
@@ -705,6 +700,8 @@ static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
 	mutex_unlock(&gpu->lock);
 }
 
+void msm_gpu_fault_crashstate_capture(struct msm_gpu *gpu, struct msm_gpu_fault_info *fault_info);
+
 /*
  * Simple macro to semi-cleanly add the MAP_PRIV flag for targets that can
  * support expanded privileges
diff --git a/drivers/gpu/drm/msm/msm_iommu.c b/drivers/gpu/drm/msm/msm_iommu.c
index fd73dcd3f30e..739ce2c283a4 100644
--- a/drivers/gpu/drm/msm/msm_iommu.c
+++ b/drivers/gpu/drm/msm/msm_iommu.c
@@ -345,7 +345,6 @@ static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev
 		unsigned long iova, int flags, void *arg)
 {
 	struct msm_iommu *iommu = arg;
-	struct msm_mmu *mmu = &iommu->base;
 	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(iommu->base.dev);
 	struct adreno_smmu_fault_info info, *ptr = NULL;
 
@@ -359,9 +358,6 @@ static int msm_gpu_fault_handler(struct iommu_domain *domain, struct device *dev
 
 	pr_warn_ratelimited("*** fault: iova=%16lx, flags=%d\n", iova, flags);
 
-	if (mmu->funcs->resume_translation)
-		mmu->funcs->resume_translation(mmu);
-
 	return 0;
 }
 
@@ -376,12 +372,12 @@ static int msm_disp_fault_handler(struct iommu_domain *domain, struct device *de
 	return -ENOSYS;
 }
 
-static void msm_iommu_resume_translation(struct msm_mmu *mmu)
+static void msm_iommu_set_stall(struct msm_mmu *mmu, bool enable)
 {
 	struct adreno_smmu_priv *adreno_smmu = dev_get_drvdata(mmu->dev);
 
-	if (adreno_smmu->resume_translation)
-		adreno_smmu->resume_translation(adreno_smmu->cookie, true);
+	if (adreno_smmu->set_stall)
+		adreno_smmu->set_stall(adreno_smmu->cookie, enable);
 }
 
 static void msm_iommu_detach(struct msm_mmu *mmu)
@@ -431,7 +427,7 @@ static const struct msm_mmu_funcs funcs = {
 		.map = msm_iommu_map,
 		.unmap = msm_iommu_unmap,
 		.destroy = msm_iommu_destroy,
-		.resume_translation = msm_iommu_resume_translation,
+		.set_stall = msm_iommu_set_stall,
 };
 
 struct msm_mmu *msm_iommu_new(struct device *dev, unsigned long quirks)
diff --git a/drivers/gpu/drm/msm/msm_mmu.h b/drivers/gpu/drm/msm/msm_mmu.h
index daf91529e02b..0c694907140d 100644
--- a/drivers/gpu/drm/msm/msm_mmu.h
+++ b/drivers/gpu/drm/msm/msm_mmu.h
@@ -15,7 +15,7 @@ struct msm_mmu_funcs {
 			size_t len, int prot);
 	int (*unmap)(struct msm_mmu *mmu, uint64_t iova, size_t len);
 	void (*destroy)(struct msm_mmu *mmu);
-	void (*resume_translation)(struct msm_mmu *mmu);
+	void (*set_stall)(struct msm_mmu *mmu, bool enable);
 };
 
 enum msm_mmu_type {
diff --git a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
index 5a6ae9fc3194..462713401622 100644
--- a/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
+++ b/drivers/gpu/drm/msm/registers/adreno/adreno_pm4.xml
@@ -2255,7 +2255,8 @@ opcode: CP_LOAD_STATE4 (30) (4 dwords)
 	<reg32 offset="0" name="0">
 		<bitfield name="CLEAR_ON_CHIP_TS" pos="0" type="boolean"/>
 		<bitfield name="CLEAR_RESOURCE_TABLE" pos="1" type="boolean"/>
-		<bitfield name="CLEAR_GLOBAL_LOCAL_TS" pos="2" type="boolean"/>
+		<bitfield name="CLEAR_BV_BR_COUNTER" pos="2" type="boolean"/>
+		<bitfield name="RESET_GLOBAL_LOCAL_TS" pos="3" type="boolean"/>
 	</reg32>
 </domain>
 
diff --git a/drivers/gpu/drm/msm/registers/gen_header.py b/drivers/gpu/drm/msm/registers/gen_header.py
index 3926485bb197..a409404627c7 100644
--- a/drivers/gpu/drm/msm/registers/gen_header.py
+++ b/drivers/gpu/drm/msm/registers/gen_header.py
@@ -11,6 +11,7 @@ import collections
 import argparse
 import time
 import datetime
+import re
 
 class Error(Exception):
 	def __init__(self, message):
@@ -877,13 +878,14 @@ The rules-ng-ng source files this header was generated from are:
 """)
 	maxlen = 0
 	for filepath in p.xml_files:
-		maxlen = max(maxlen, len(filepath))
+		new_filepath = re.sub("^.+drivers","drivers",filepath)
+		maxlen = max(maxlen, len(new_filepath))
 	for filepath in p.xml_files:
-		pad = " " * (maxlen - len(filepath))
+		pad = " " * (maxlen - len(new_filepath))
 		filesize = str(os.path.getsize(filepath))
 		filesize = " " * (7 - len(filesize)) + filesize
 		filetime = time.ctime(os.path.getmtime(filepath))
-		print("- " + filepath + pad + " (" + filesize + " bytes, from " + filetime + ")")
+		print("- " + new_filepath + pad + " (" + filesize + " bytes, from <stripped>)")
 	if p.copyright_year:
 		current_year = str(datetime.date.today().year)
 		print()