Merge tag 'drm-msm-fixes-2023-03-09' of https://gitlab.freedesktop.org/drm/msm into drm-fixes

msm-fixes for v6.3-rc2

- Fix for possible invalid ptr free in submit ioctl syncobj cleanup path.
- Synchronize GMU removal in driver teardown path
- a5xx preemption fixes
- Fix runpm imbalance at unbind
- DPU hw catalog fixes:
 - set DPU_MDP_PERIPH_0_REMOVED for sc8280xp as this is another chipset
   where the PERIPH_0 block of registers is not there
 - fix the DPU features supported in QCM2290 by comparing it with the
   downstream device tree
 - fix the length of registers in the sc7180_ctl from 0xe4 to 0x1dc
 - fix the max mixer line width for sm6115 and qcm2290 chipsets in the
   DPU catalog
 - fix the scaler version on sm8550, sc8280xp, sm8450, sm8250, sm8350
   and sm6115. This was incorrectly populated on the SW version of the
   scaler library and  not the scaler HW version
 - Drop dim layer support for msm8998 as its not indicated to be
   supported in the downstream DTSI
 - fix the DPU_CLK_CTRL bits for msm 8998 sspp blocks
 - Use DPU_CLK_CTRL_DMA* prefix instead of DPU_CLK_CTRL_CURSOR*
   for all chipsets for the DMA sspp blocks
 - fix the ping-pong block base address for sc7280 in the DPU HW catalog
- Fix stack corruption issue in the dpu_hw_ctl_setup_blendstage() function
  as it was causing a negative left shift by protecting against an invalid
  index
- Clear the DSPP reservations in dpu_rm_release(). This was missed out and
  as as result the DSPP was not released from the resource manager global
  state.
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Rob Clark <robdclark@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/CAF6AEGvH+VH_Wx3mFMG51CMnoiU06CM-+-WMhM73M42Qx7Bp4A@mail.gmail.com

drivers/gpu/drm/msm/Kconfig

@@ -23,7 +23,6 @@ config DRM_MSM
 	select SHMEM
 	select TMPFS
 	select QCOM_SCM
-	select DEVFREQ_GOV_SIMPLE_ONDEMAND
 	select WANT_DEV_COREDUMP
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select SYNC_FILE

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

@@ -151,8 +151,8 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
 	OUT_RING(ring, 1);
 
 	/* Enable local preemption for finegrain preemption */
-	OUT_PKT7(ring, CP_PREEMPT_ENABLE_GLOBAL, 1);
-	OUT_RING(ring, 0x02);
+	OUT_PKT7(ring, CP_PREEMPT_ENABLE_LOCAL, 1);
+	OUT_RING(ring, 0x1);
 
 	/* Allow CP_CONTEXT_SWITCH_YIELD packets in the IB2 */
 	OUT_PKT7(ring, CP_YIELD_ENABLE, 1);
@@ -806,7 +806,7 @@ static int a5xx_hw_init(struct msm_gpu *gpu)
 	gpu_write(gpu, REG_A5XX_RBBM_AHB_CNTL2, 0x0000003F);
 
 	/* Set the highest bank bit */
-	if (adreno_is_a540(adreno_gpu))
+	if (adreno_is_a540(adreno_gpu) || adreno_is_a530(adreno_gpu))
 		regbit = 2;
 	else
 		regbit = 1;

drivers/gpu/drm/msm/adreno/a5xx_preempt.c

@@ -63,7 +63,7 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu)
 		struct msm_ringbuffer *ring = gpu->rb[i];
 
 		spin_lock_irqsave(&ring->preempt_lock, flags);
-		empty = (get_wptr(ring) == ring->memptrs->rptr);
+		empty = (get_wptr(ring) == gpu->funcs->get_rptr(gpu, ring));
 		spin_unlock_irqrestore(&ring->preempt_lock, flags);
 
 		if (!empty)
@@ -207,6 +207,7 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu)
 		a5xx_gpu->preempt[i]->wptr = 0;
 		a5xx_gpu->preempt[i]->rptr = 0;
 		a5xx_gpu->preempt[i]->rbase = gpu->rb[i]->iova;
+		a5xx_gpu->preempt[i]->rptr_addr = shadowptr(a5xx_gpu, gpu->rb[i]);
 	}
 
 	/* Write a 0 to signal that we aren't switching pagetables */
@@ -257,7 +258,6 @@ static int preempt_init_ring(struct a5xx_gpu *a5xx_gpu,
 	ptr->data = 0;
 	ptr->cntl = MSM_GPU_RB_CNTL_DEFAULT | AXXX_CP_RB_CNTL_NO_UPDATE;
 
-	ptr->rptr_addr = shadowptr(a5xx_gpu, ring);
 	ptr->counter = counters_iova;
 
 	return 0;

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

@@ -974,7 +974,7 @@ int a6xx_gmu_resume(struct a6xx_gpu *a6xx_gpu)
 	int status, ret;
 
 	if (WARN(!gmu->initialized, "The GMU is not set up yet\n"))
-		return 0;
+		return -EINVAL;
 
 	gmu->hung = false;
 

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

@@ -1746,7 +1746,9 @@ static void a6xx_destroy(struct msm_gpu *gpu)
 
 	a6xx_llc_slices_destroy(a6xx_gpu);
 
+	mutex_lock(&a6xx_gpu->gmu.lock);
 	a6xx_gmu_remove(a6xx_gpu);
+	mutex_unlock(&a6xx_gpu->gmu.lock);
 
 	adreno_gpu_cleanup(adreno_gpu);
 

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

@@ -558,7 +558,8 @@ static void adreno_unbind(struct device *dev, struct device *master,
 	struct msm_drm_private *priv = dev_get_drvdata(master);
 	struct msm_gpu *gpu = dev_to_gpu(dev);
 
-	WARN_ON_ONCE(adreno_system_suspend(dev));
+	if (pm_runtime_enabled(dev))
+		WARN_ON_ONCE(adreno_system_suspend(dev));
 	gpu->funcs->destroy(gpu);
 
 	priv->gpu_pdev = NULL;

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

@@ -515,6 +515,8 @@ enum dpu_clk_ctrl_type {
 	DPU_CLK_CTRL_DMA1,
 	DPU_CLK_CTRL_DMA2,
 	DPU_CLK_CTRL_DMA3,
+	DPU_CLK_CTRL_DMA4,
+	DPU_CLK_CTRL_DMA5,
 	DPU_CLK_CTRL_CURSOR0,
 	DPU_CLK_CTRL_CURSOR1,
 	DPU_CLK_CTRL_INLINE_ROT0_SSPP,

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

@@ -446,7 +446,9 @@ static void dpu_hw_ctl_setup_blendstage(struct dpu_hw_ctl *ctx,
 			 * CTL_LAYER has 3-bit field (and extra bits in EXT register),
 			 * all EXT registers has 4-bit fields.
 			 */
-			if (cfg->idx == 0) {
+			if (cfg->idx == -1) {
+				continue;
+			} else if (cfg->idx == 0) {
 				mixercfg[0] |= mix << cfg->shift;
 				mixercfg[1] |= ext << cfg->ext_shift;
 			} else {

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

@@ -577,6 +577,8 @@ void dpu_rm_release(struct dpu_global_state *global_state,
 		ARRAY_SIZE(global_state->ctl_to_enc_id), enc->base.id);
 	_dpu_rm_clear_mapping(global_state->dsc_to_enc_id,
 		ARRAY_SIZE(global_state->dsc_to_enc_id), enc->base.id);
+	_dpu_rm_clear_mapping(global_state->dspp_to_enc_id,
+		ARRAY_SIZE(global_state->dspp_to_enc_id), enc->base.id);
 }
 
 int dpu_rm_reserve(

drivers/gpu/drm/msm/msm_gem_submit.c

@@ -637,8 +637,8 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev,
 	int ret = 0;
 	uint32_t i, j;
 
-	post_deps = kmalloc_array(nr_syncobjs, sizeof(*post_deps),
-	                          GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+	post_deps = kcalloc(nr_syncobjs, sizeof(*post_deps),
+			    GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
 	if (!post_deps)
 		return ERR_PTR(-ENOMEM);
 
@@ -653,7 +653,6 @@ static struct msm_submit_post_dep *msm_parse_post_deps(struct drm_device *dev,
 		}
 
 		post_deps[i].point = syncobj_desc.point;
-		post_deps[i].chain = NULL;
 
 		if (syncobj_desc.flags) {
 			ret = -EINVAL;