drm/msm/a6xx: Make crashstate capture IFPC safe

Now with IFPC, GX domain can collapse as soon as GPU becomes IDLE. So
add gx_is_on check before accessing any GX registers during crashstate
capture and recovery.

Signed-off-by: Akhil P Oommen <akhilpo@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/673383/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>

Author: akhilpo-qcom

drivers/gpu/drm/msm/adreno/a6xx_gmu.c

@@ -101,6 +101,10 @@ bool a6xx_gmu_gx_is_on(struct a6xx_gmu *gmu)
 	if (!gmu->initialized)
 		return false;
 
+	/* If GMU is absent, then GX power domain is ON as long as GPU is in active state */
+	if (adreno_has_gmu_wrapper(adreno_gpu))
+		return true;
+
 	val = gmu_read(gmu, REG_A6XX_GMU_SPTPRAC_PWR_CLK_STATUS);
 
 	if (adreno_is_a7xx(adreno_gpu))

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

@@ -1537,21 +1537,25 @@ static void a6xx_recover(struct msm_gpu *gpu)
 
 	adreno_dump_info(gpu);
 
-	for (i = 0; i < 8; i++)
-		DRM_DEV_INFO(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i,
-			gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(i)));
+	if (a6xx_gmu_gx_is_on(&a6xx_gpu->gmu)) {
+		/* Sometimes crashstate capture is skipped, so SQE should be halted here again */
+		gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3);
 
-	if (hang_debug)
-		a6xx_dump(gpu);
+		for (i = 0; i < 8; i++)
+			DRM_DEV_INFO(&gpu->pdev->dev, "CP_SCRATCH_REG%d: %u\n", i,
+				gpu_read(gpu, REG_A6XX_CP_SCRATCH_REG(i)));
+
+		if (hang_debug)
+			a6xx_dump(gpu);
+
+	}
 
 	/*
 	 * To handle recovery specific sequences during the rpm suspend we are
 	 * about to trigger
 	 */
-	a6xx_gpu->hung = true;
 
-	/* Halt SQE first */
-	gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3);
+	a6xx_gpu->hung = true;
 
 	pm_runtime_dont_use_autosuspend(&gpu->pdev->dev);
 
@@ -2415,6 +2419,13 @@ static uint32_t a6xx_get_rptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	if (adreno_gpu->base.hw_apriv || a6xx_gpu->has_whereami)
 		return a6xx_gpu->shadow[ring->id];
 
+	/*
+	 * This is true only on an A6XX_GEN1 with GMU, has IFPC enabled and a super old SQE firmware
+	 * without 'whereami' support
+	 */
+	WARN_ONCE((to_adreno_gpu(gpu)->info->quirks & ADRENO_QUIRK_IFPC),
+		"Can't read CP_RB_RPTR register reliably\n");
+
 	return ring->memptrs->rptr = gpu_read(gpu, REG_A6XX_CP_RB_RPTR);
 }
 

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

@@ -1586,8 +1586,7 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 	struct a6xx_gpu *a6xx_gpu = to_a6xx_gpu(adreno_gpu);
 	struct a6xx_gpu_state *a6xx_state = kzalloc(sizeof(*a6xx_state),
 		GFP_KERNEL);
-	bool stalled = !!(gpu_read(gpu, REG_A6XX_RBBM_STATUS3) &
-			A6XX_RBBM_STATUS3_SMMU_STALLED_ON_FAULT);
+	bool stalled;
 
 	if (!a6xx_state)
 		return ERR_PTR(-ENOMEM);
@@ -1608,15 +1607,20 @@ struct msm_gpu_state *a6xx_gpu_state_get(struct msm_gpu *gpu)
 	}
 
 	/* If GX isn't on the rest of the data isn't going to be accessible */
-	if (!adreno_has_gmu_wrapper(adreno_gpu) && !a6xx_gmu_gx_is_on(&a6xx_gpu->gmu))
+	if (!a6xx_gmu_gx_is_on(&a6xx_gpu->gmu))
 		return &a6xx_state->base;
 
+	/* Halt SQE first */
+	gpu_write(gpu, REG_A6XX_CP_SQE_CNTL, 3);
+
 	/* Get the banks of indexed registers */
 	if (adreno_is_a7xx(adreno_gpu))
 		a7xx_get_indexed_registers(gpu, a6xx_state);
 	else
 		a6xx_get_indexed_registers(gpu, a6xx_state);
 
+	stalled = !!(gpu_read(gpu, REG_A6XX_RBBM_STATUS3) &
+			A6XX_RBBM_STATUS3_SMMU_STALLED_ON_FAULT);
 	/*
 	 * Try to initialize the crashdumper, if we are not dumping state
 	 * with the SMMU stalled.  The crashdumper needs memory access to