drm/msm: GPU recovery, IRQ, and state capture fixes

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

@@ -1281,6 +1281,11 @@ static irqreturn_t a5xx_irq(struct msm_gpu *gpu)
 		status & ~A5XX_RBBM_INT_0_MASK_RBBM_AHB_ERROR);
 
 	if (priv->disable_err_irq) {
+		/* Turn off interrupts to avoid interrupt storm */
+		gpu_write(gpu, REG_A5XX_RBBM_INT_0_MASK,
+			       A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS |
+			       A5XX_RBBM_INT_0_MASK_CP_SW);
+
 		status &= A5XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS |
 			  A5XX_RBBM_INT_0_MASK_CP_SW;
 	}

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

@@ -1915,8 +1915,11 @@ static irqreturn_t a6xx_irq(struct msm_gpu *gpu)
 
 	gpu_write(gpu, REG_A6XX_RBBM_INT_CLEAR_CMD, status);
 
-	if (priv->disable_err_irq)
+	if (priv->disable_err_irq) {
+		/* Turn off interrupts to avoid interrupt storm */
+		gpu_write(gpu, REG_A6XX_RBBM_INT_0_MASK, A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS);
 		status &= A6XX_RBBM_INT_0_MASK_CP_CACHE_FLUSH_TS;
+	}
 
 	if (status & A6XX_RBBM_INT_0_MASK_RBBM_HANG_DETECT)
 		a6xx_fault_detect_irq(gpu);

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

@@ -1244,9 +1244,12 @@ static void a6xx_get_gmu_registers(struct msm_gpu *gpu,
 	_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gmu_reglist[1],
 		&a6xx_state->gmu_registers[1], true);
 
-	if (adreno_is_a621(adreno_gpu) || adreno_is_a623(adreno_gpu))
+	if (adreno_is_a621(adreno_gpu))
 		_a6xx_get_gmu_registers(gpu, a6xx_state, &a621_gpucc_reg,
 			&a6xx_state->gmu_registers[2], false);
+	else if (adreno_is_a623(adreno_gpu) || adreno_is_a663(adreno_gpu))
+		_a6xx_get_gmu_registers(gpu, a6xx_state, &a623_gpucc_reg,
+			&a6xx_state->gmu_registers[2], false);
 	else
 		_a6xx_get_gmu_registers(gpu, a6xx_state, &a6xx_gpucc_reg,
 			&a6xx_state->gmu_registers[2], false);

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

@@ -377,6 +377,17 @@ static const u32 a6xx_gmu_gpucc_registers[] = {
 };
 
 static const u32 a621_gmu_gpucc_registers[] = {
+	/* GPU CC */
+	0x24000, 0x2400e, 0x24400, 0x2440e, 0x24800, 0x24805, 0x24c00, 0x24cff,
+	0x25800, 0x25804, 0x25c00, 0x25c04, 0x26000, 0x26004, 0x26400, 0x26405,
+	0x26414, 0x2641d, 0x2642a, 0x26430, 0x26432, 0x26432, 0x26441, 0x26455,
+	0x26466, 0x26468, 0x26478, 0x2647a, 0x26489, 0x2648a, 0x2649c, 0x2649e,
+	0x264a0, 0x264a3, 0x264b3, 0x264b5, 0x264c5, 0x264c7, 0x264d6, 0x264d8,
+	0x264e8, 0x264e9, 0x264f9, 0x264fc, 0x2650b, 0x2650c, 0x2651c, 0x2651e,
+	0x26540, 0x26570, 0x26600, 0x26616, 0x26620, 0x2662d,
+};
+
+static const u32 a623_gmu_gpucc_registers[] = {
 	/* GPU CC */
 	0x24000, 0x2400e, 0x24400, 0x2440e, 0x25800, 0x25804, 0x25c00, 0x25c04,
 	0x26000, 0x26004, 0x26400, 0x26405, 0x26414, 0x2641d, 0x2642a, 0x26430,
@@ -402,6 +413,7 @@ static const struct a6xx_registers a6xx_gmu_reglist[] = {
 
 static const struct a6xx_registers a6xx_gpucc_reg = REGS(a6xx_gmu_gpucc_registers, 0, 0);
 static const struct a6xx_registers a621_gpucc_reg = REGS(a621_gmu_gpucc_registers, 0, 0);
+static const struct a6xx_registers a623_gpucc_reg = REGS(a623_gmu_gpucc_registers, 0, 0);
 
 static u32 a6xx_get_cp_roq_size(struct msm_gpu *gpu);
 static u32 a7xx_get_cp_roq_size(struct msm_gpu *gpu);

drivers/gpu/drm/msm/msm_gpu.c

@@ -504,6 +504,8 @@ static void recover_worker(struct kthread_work *work)
 		 */
 		if (!vm->managed)
 			msm_gem_vm_unusable(submit->vm);
+
+		put_task_struct(task);
 	}
 
 	get_comm_cmdline(submit, &comm, &cmd);
@@ -547,32 +549,32 @@ static void recover_worker(struct kthread_work *work)
 		msm_update_fence(ring->fctx, fence);
 	}
 
-	if (msm_gpu_active(gpu)) {
-		/* retire completed submits, plus the one that hung: */
-		retire_submits(gpu);
+	priv->disable_err_irq = false;
 
-		gpu->funcs->recover(gpu);
+	gpu->funcs->recover(gpu);
 
-		/*
-		 * Replay all remaining submits starting with highest priority
-		 * ring
-		 */
-		for (i = 0; i < gpu->nr_rings; i++) {
-			struct msm_ringbuffer *ring = gpu->rb[i];
-			unsigned long flags;
+	/* retire completed submits, plus the one that hung: */
+	retire_submits(gpu);
 
-			spin_lock_irqsave(&ring->submit_lock, flags);
-			list_for_each_entry(submit, &ring->submits, node) {
-				/*
-				 * If the submit uses an unusable vm make sure
-				 * we don't actually run it
-				 */
-				if (to_msm_vm(submit->vm)->unusable)
-					submit->nr_cmds = 0;
-				gpu->funcs->submit(gpu, submit);
-			}
-			spin_unlock_irqrestore(&ring->submit_lock, flags);
+	/*
+	 * Replay all remaining submits starting with highest priority
+	 * ring
+	 */
+	for (i = 0; i < gpu->nr_rings; i++) {
+		struct msm_ringbuffer *ring = gpu->rb[i];
+		unsigned long flags;
+
+		spin_lock_irqsave(&ring->submit_lock, flags);
+		list_for_each_entry(submit, &ring->submits, node) {
+			/*
+			 * If the submit uses an unusable vm make sure
+			 * we don't actually run it
+			 */
+			if (to_msm_vm(submit->vm)->unusable)
+				submit->nr_cmds = 0;
+			gpu->funcs->submit(gpu, submit);
 		}
+		spin_unlock_irqrestore(&ring->submit_lock, flags);
 	}
 
 	pm_runtime_put(&gpu->pdev->dev);