Merge tag 'drm-fixes-2026-01-30' of https://gitlab.freedesktop.org/drm/kernel

Pull drm fixes from Dave Airlie:
 "Seems to be a bit quieter this week, mostly xe and amdgpu, with msm
  and imx fixes and one WARN_ON from user blocked. Nothing of note
  outstanding either.

  uapi:
   - Fix a WARN_ON() when passing an invalid handle to
     drm_gem_change_handle_ioctl()

  msm:
   - GPU:
      - Fix bogus hwcg register update for a690

  xe:
   - Skip address copy for sync-only execs
   - Fix a WA
   - Derive mem_copy cap from graphics version
   - Fix is_bound() pci_dev lifetime
   - xe nvm cleanup fixes

  amdgpu:
   - SMU 13 fixes
   - SMU 14 fixes
   - GPUVM fault filter fix
   - Powergating fix
   - HDMI debounce fix
   - Xclk fix for soc21 APUs
   - Fix COND_EXEC handling for GC 11
   - GC 10-12 KGQ init fixes
   - GC 11-12 KGQ reset fixes

  imx/tve:
   - drop ddc device reference when unloading"

* tag 'drm-fixes-2026-01-30' of https://gitlab.freedesktop.org/drm/kernel: (21 commits)
  drm/xe/nvm: Fix double-free on aux add failure
  drm/xe/nvm: Manage nvm aux cleanup with devres
  drm/amdgpu/gfx12: adjust KGQ reset sequence
  drm/amdgpu/gfx11: adjust KGQ reset sequence
  drm/amdgpu/gfx12: fix wptr reset in KGQ init
  drm/amdgpu/gfx11: fix wptr reset in KGQ init
  drm/amdgpu/gfx10: fix wptr reset in KGQ init
  drm/xe/configfs: Fix is_bound() pci_dev lifetime
  drm/amdgpu: Fix cond_exec handling in amdgpu_ib_schedule()
  drm/amdgpu/soc21: fix xclk for APUs
  drm/amd/display: Clear HDMI HPD pending work only if it is enabled
  drm/imx/tve: fix probe device leak
  drm/amd/pm: fix race in power state check before mutex lock
  drm/amdgpu: fix NULL pointer dereference in amdgpu_gmc_filter_faults_remove
  drm/amd/pm: fix smu v14 soft clock frequency setting issue
  drm/amd/pm: fix smu v13 soft clock frequency setting issue
  drm/xe: derive mem copy capability from graphics version
  drm/xe/xelp: Fix Wa_18022495364
  drm/xe: Skip address copy for sync-only execs
  drm: Do not allow userspace to trigger kernel warnings in drm_gem_change_handle_ioctl()
  ...

23 files changed, 117 insertions, 86 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
index 7e623f91f2d7..d9c7ad297293 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
@@ -498,8 +498,13 @@ void amdgpu_gmc_filter_faults_remove(struct amdgpu_device *adev, uint64_t addr,
 
 	if (adev->irq.retry_cam_enabled)
 		return;
+	else if (adev->irq.ih1.ring_size)
+		ih = &adev->irq.ih1;
+	else if (adev->irq.ih_soft.enabled)
+		ih = &adev->irq.ih_soft;
+	else
+		return;
 
-	ih = &adev->irq.ih1;
 	/* Get the WPTR of the last entry in IH ring */
 	last_wptr = amdgpu_ih_get_wptr(adev, ih);
 	/* Order wptr with ring data. */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 72ec455fa932..44f230d67da2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -235,7 +235,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
 
 	amdgpu_ring_ib_begin(ring);
 
-	if (ring->funcs->emit_gfx_shadow)
+	if (ring->funcs->emit_gfx_shadow && adev->gfx.cp_gfx_shadow)
 		amdgpu_ring_emit_gfx_shadow(ring, shadow_va, csa_va, gds_va,
 					    init_shadow, vmid);
 
@@ -291,7 +291,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned int num_ibs,
 				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
 	}
 
-	if (ring->funcs->emit_gfx_shadow && ring->funcs->init_cond_exec) {
+	if (ring->funcs->emit_gfx_shadow && ring->funcs->init_cond_exec &&
+	    adev->gfx.cp_gfx_shadow) {
 		amdgpu_ring_emit_gfx_shadow(ring, 0, 0, 0, false, 0);
 		amdgpu_ring_init_cond_exec(ring, ring->cond_exe_gpu_addr);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
index d75b9940f248..fc65fb36e115 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v10_0.c
@@ -6879,7 +6879,7 @@ static int gfx_v10_0_kgq_init_queue(struct amdgpu_ring *ring, bool reset)
 			memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset the ring */
 		ring->wptr = 0;
-		*ring->wptr_cpu_addr = 0;
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
 		amdgpu_ring_clear_ring(ring);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
index 8a2ee2de390f..e642236ea2c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
@@ -4201,7 +4201,7 @@ static int gfx_v11_0_kgq_init_queue(struct amdgpu_ring *ring, bool reset)
 			memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset the ring */
 		ring->wptr = 0;
-		*ring->wptr_cpu_addr = 0;
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
 		amdgpu_ring_clear_ring(ring);
 	}
 
@@ -6823,11 +6823,12 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring,
 			       struct amdgpu_fence *timedout_fence)
 {
 	struct amdgpu_device *adev = ring->adev;
+	bool use_mmio = false;
 	int r;
 
 	amdgpu_ring_reset_helper_begin(ring, timedout_fence);
 
-	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, false);
+	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, use_mmio);
 	if (r) {
 
 		dev_warn(adev->dev, "reset via MES failed and try pipe reset %d\n", r);
@@ -6836,16 +6837,18 @@ static int gfx_v11_0_reset_kgq(struct amdgpu_ring *ring,
 			return r;
 	}
 
-	r = gfx_v11_0_kgq_init_queue(ring, true);
-	if (r) {
-		dev_err(adev->dev, "failed to init kgq\n");
-		return r;
-	}
+	if (use_mmio) {
+		r = gfx_v11_0_kgq_init_queue(ring, true);
+		if (r) {
+			dev_err(adev->dev, "failed to init kgq\n");
+			return r;
+		}
 
-	r = amdgpu_mes_map_legacy_queue(adev, ring);
-	if (r) {
-		dev_err(adev->dev, "failed to remap kgq\n");
-		return r;
+		r = amdgpu_mes_map_legacy_queue(adev, ring);
+		if (r) {
+			dev_err(adev->dev, "failed to remap kgq\n");
+			return r;
+		}
 	}
 
 	return amdgpu_ring_reset_helper_end(ring, timedout_fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
index b786967022d2..4aab89a9ab40 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v12_0.c
@@ -3079,7 +3079,7 @@ static int gfx_v12_0_kgq_init_queue(struct amdgpu_ring *ring, bool reset)
 			memcpy_toio(mqd, adev->gfx.me.mqd_backup[mqd_idx], sizeof(*mqd));
 		/* reset the ring */
 		ring->wptr = 0;
-		*ring->wptr_cpu_addr = 0;
+		atomic64_set((atomic64_t *)ring->wptr_cpu_addr, 0);
 		amdgpu_ring_clear_ring(ring);
 	}
 
@@ -5297,11 +5297,12 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring,
 			       struct amdgpu_fence *timedout_fence)
 {
 	struct amdgpu_device *adev = ring->adev;
+	bool use_mmio = false;
 	int r;
 
 	amdgpu_ring_reset_helper_begin(ring, timedout_fence);
 
-	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, false);
+	r = amdgpu_mes_reset_legacy_queue(ring->adev, ring, vmid, use_mmio);
 	if (r) {
 		dev_warn(adev->dev, "reset via MES failed and try pipe reset %d\n", r);
 		r = gfx_v12_reset_gfx_pipe(ring);
@@ -5309,16 +5310,18 @@ static int gfx_v12_0_reset_kgq(struct amdgpu_ring *ring,
 			return r;
 	}
 
-	r = gfx_v12_0_kgq_init_queue(ring, true);
-	if (r) {
-		dev_err(adev->dev, "failed to init kgq\n");
-		return r;
-	}
+	if (use_mmio) {
+		r = gfx_v12_0_kgq_init_queue(ring, true);
+		if (r) {
+			dev_err(adev->dev, "failed to init kgq\n");
+			return r;
+		}
 
-	r = amdgpu_mes_map_legacy_queue(adev, ring);
-	if (r) {
-		dev_err(adev->dev, "failed to remap kgq\n");
-		return r;
+		r = amdgpu_mes_map_legacy_queue(adev, ring);
+		if (r) {
+			dev_err(adev->dev, "failed to remap kgq\n");
+			return r;
+		}
 	}
 
 	return amdgpu_ring_reset_helper_end(ring, timedout_fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/soc21.c b/drivers/gpu/drm/amd/amdgpu/soc21.c
index ad36c96478a8..25536d89635d 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc21.c
+++ b/drivers/gpu/drm/amd/amdgpu/soc21.c
@@ -225,7 +225,13 @@ static u32 soc21_get_config_memsize(struct amdgpu_device *adev)
 
 static u32 soc21_get_xclk(struct amdgpu_device *adev)
 {
-	return adev->clock.spll.reference_freq;
+	u32 reference_clock = adev->clock.spll.reference_freq;
+
+	/* reference clock is actually 99.81 Mhz rather than 100 Mhz */
+	if ((adev->flags & AMD_IS_APU) && reference_clock == 10000)
+		return 9981;
+
+	return reference_clock;
 }
 
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 1ea5a250440f..a8a59126b2d2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7754,10 +7754,12 @@ static void amdgpu_dm_connector_destroy(struct drm_connector *connector)
 		drm_dp_mst_topology_mgr_destroy(&aconnector->mst_mgr);
 
 	/* Cancel and flush any pending HDMI HPD debounce work */
-	cancel_delayed_work_sync(&aconnector->hdmi_hpd_debounce_work);
-	if (aconnector->hdmi_prev_sink) {
-		dc_sink_release(aconnector->hdmi_prev_sink);
-		aconnector->hdmi_prev_sink = NULL;
+	if (aconnector->hdmi_hpd_debounce_delay_ms) {
+		cancel_delayed_work_sync(&aconnector->hdmi_hpd_debounce_work);
+		if (aconnector->hdmi_prev_sink) {
+			dc_sink_release(aconnector->hdmi_prev_sink);
+			aconnector->hdmi_prev_sink = NULL;
+		}
 	}
 
 	if (aconnector->bl_idx != -1) {
diff --git a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
index 79b174e5326d..302af1fb6901 100644
--- a/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/pm/amdgpu_dpm.c
@@ -80,15 +80,15 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev,
 	enum ip_power_state pwr_state = gate ? POWER_STATE_OFF : POWER_STATE_ON;
 	bool is_vcn = block_type == AMD_IP_BLOCK_TYPE_VCN;
 
+	mutex_lock(&adev->pm.mutex);
+
 	if (atomic_read(&adev->pm.pwr_state[block_type]) == pwr_state &&
 			(!is_vcn || adev->vcn.num_vcn_inst == 1)) {
 		dev_dbg(adev->dev, "IP block%d already in the target %s state!",
 				block_type, gate ? "gate" : "ungate");
-		return 0;
+		goto out_unlock;
 	}
 
-	mutex_lock(&adev->pm.mutex);
-
 	switch (block_type) {
 	case AMD_IP_BLOCK_TYPE_UVD:
 	case AMD_IP_BLOCK_TYPE_VCE:
@@ -115,6 +115,7 @@ int amdgpu_dpm_set_powergating_by_smu(struct amdgpu_device *adev,
 	if (!ret)
 		atomic_set(&adev->pm.pwr_state[block_type], pwr_state);
 
+out_unlock:
 	mutex_unlock(&adev->pm.mutex);
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
index 4263798d716b..8e592a477c33 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
@@ -56,6 +56,7 @@
 #define SMUQ10_TO_UINT(x) ((x) >> 10)
 #define SMUQ10_FRAC(x) ((x) & 0x3ff)
 #define SMUQ10_ROUND(x) ((SMUQ10_TO_UINT(x)) + ((SMUQ10_FRAC(x)) >= 0x200))
+#define SMU_V13_SOFT_FREQ_ROUND(x)	((x) + 1)
 
 extern const int pmfw_decoded_link_speed[5];
 extern const int pmfw_decoded_link_width[7];
diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
index 29a4583db873..0b1e6f25e611 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
+++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v14_0.h
@@ -57,6 +57,7 @@ extern const int decoded_link_width[8];
 
 #define DECODE_GEN_SPEED(gen_speed_idx)		(decoded_link_speed[gen_speed_idx])
 #define DECODE_LANE_WIDTH(lane_width_idx)	(decoded_link_width[lane_width_idx])
+#define SMU_V14_SOFT_FREQ_ROUND(x)	((x) + 1)
 
 struct smu_14_0_max_sustainable_clocks {
 	uint32_t display_clock;
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
index a89075e25717..2efd914d81e5 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
@@ -1555,6 +1555,7 @@ int smu_v13_0_set_soft_freq_limited_range(struct smu_context *smu,
 		return clk_id;
 
 	if (max > 0) {
+		max = SMU_V13_SOFT_FREQ_ROUND(max);
 		if (automatic)
 			param = (uint32_t)((clk_id << 16) | 0xffff);
 		else
diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index f2a16dfee599..06a81533759c 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -1178,6 +1178,7 @@ int smu_v14_0_set_soft_freq_limited_range(struct smu_context *smu,
 		return clk_id;
 
 	if (max > 0) {
+		max = SMU_V14_SOFT_FREQ_ROUND(max);
 		if (automatic)
 			param = (uint32_t)((clk_id << 16) | 0xffff);
 		else
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index e4df43427394..25f68fed9b48 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -960,16 +960,21 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data,
 {
 	struct drm_gem_change_handle *args = data;
 	struct drm_gem_object *obj;
-	int ret;
+	int handle, ret;
 
 	if (!drm_core_check_feature(dev, DRIVER_GEM))
 		return -EOPNOTSUPP;
 
+	/* idr_alloc() limitation. */
+	if (args->new_handle > INT_MAX)
+		return -EINVAL;
+	handle = args->new_handle;
+
 	obj = drm_gem_object_lookup(file_priv, args->handle);
 	if (!obj)
 		return -ENOENT;
 
-	if (args->handle == args->new_handle) {
+	if (args->handle == handle) {
 		ret = 0;
 		goto out;
 	}
@@ -977,18 +982,19 @@ int drm_gem_change_handle_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&file_priv->prime.lock);
 
 	spin_lock(&file_priv->table_lock);
-	ret = idr_alloc(&file_priv->object_idr, obj,
-		args->new_handle, args->new_handle + 1, GFP_NOWAIT);
+	ret = idr_alloc(&file_priv->object_idr, obj, handle, handle + 1,
+			GFP_NOWAIT);
 	spin_unlock(&file_priv->table_lock);
 
 	if (ret < 0)
 		goto out_unlock;
 
 	if (obj->dma_buf) {
-		ret = drm_prime_add_buf_handle(&file_priv->prime, obj->dma_buf, args->new_handle);
+		ret = drm_prime_add_buf_handle(&file_priv->prime, obj->dma_buf,
+					       handle);
 		if (ret < 0) {
 			spin_lock(&file_priv->table_lock);
-			idr_remove(&file_priv->object_idr, args->new_handle);
+			idr_remove(&file_priv->object_idr, handle);
 			spin_unlock(&file_priv->table_lock);
 			goto out_unlock;
 		}
diff --git a/drivers/gpu/drm/imx/ipuv3/imx-tve.c b/drivers/gpu/drm/imx/ipuv3/imx-tve.c
index c5c6e070cc06..e861b8b9d8fa 100644
--- a/drivers/gpu/drm/imx/ipuv3/imx-tve.c
+++ b/drivers/gpu/drm/imx/ipuv3/imx-tve.c
@@ -528,6 +528,13 @@ static const struct component_ops imx_tve_ops = {
 	.bind	= imx_tve_bind,
 };
 
+static void imx_tve_put_device(void *_dev)
+{
+	struct device *dev = _dev;
+
+	put_device(dev);
+}
+
 static int imx_tve_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -549,6 +556,12 @@ static int imx_tve_probe(struct platform_device *pdev)
 	if (ddc_node) {
 		tve->ddc = of_find_i2c_adapter_by_node(ddc_node);
 		of_node_put(ddc_node);
+		if (tve->ddc) {
+			ret = devm_add_action_or_reset(dev, imx_tve_put_device,
+						       &tve->ddc->dev);
+			if (ret)
+				return ret;
+		}
 	}
 
 	tve->mode = of_get_tve_mode(np);
diff --git a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
index ac9a95aab2fb..4c042133261c 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_catalog.c
@@ -501,8 +501,6 @@ static const struct adreno_reglist a690_hwcg[] = {
 	{REG_A6XX_RBBM_CLOCK_CNTL_GMU_GX, 0x00000222},
 	{REG_A6XX_RBBM_CLOCK_DELAY_GMU_GX, 0x00000111},
 	{REG_A6XX_RBBM_CLOCK_HYST_GMU_GX, 0x00000555},
-	{REG_A6XX_GPU_GMU_AO_GMU_CGC_DELAY_CNTL, 0x10111},
-	{REG_A6XX_GPU_GMU_AO_GMU_CGC_HYST_CNTL, 0x5555},
 	{}
 };
 
diff --git a/drivers/gpu/drm/xe/xe_configfs.c b/drivers/gpu/drm/xe/xe_configfs.c
index 9f6251b1008b..82edd0466005 100644
--- a/drivers/gpu/drm/xe/xe_configfs.c
+++ b/drivers/gpu/drm/xe/xe_configfs.c
@@ -347,11 +347,10 @@ static bool is_bound(struct xe_config_group_device *dev)
 		return false;
 
 	ret = pci_get_drvdata(pdev);
-	pci_dev_put(pdev);
-
 	if (ret)
 		pci_dbg(pdev, "Already bound to driver\n");
 
+	pci_dev_put(pdev);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
index cf29e259861f..9a6d49fcd8e4 100644
--- a/drivers/gpu/drm/xe/xe_device.c
+++ b/drivers/gpu/drm/xe/xe_device.c
@@ -984,8 +984,6 @@ void xe_device_remove(struct xe_device *xe)
 {
 	xe_display_unregister(xe);
 
-	xe_nvm_fini(xe);
-
 	drm_dev_unplug(&xe->drm);
 
 	xe_bo_pci_dev_remove_all(xe);
diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
index fd9480031750..8e3614b24010 100644
--- a/drivers/gpu/drm/xe/xe_exec.c
+++ b/drivers/gpu/drm/xe/xe_exec.c
@@ -190,9 +190,9 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		goto err_syncs;
 	}
 
-	if (xe_exec_queue_is_parallel(q)) {
-		err = copy_from_user(addresses, addresses_user, sizeof(u64) *
-				     q->width);
+	if (args->num_batch_buffer && xe_exec_queue_is_parallel(q)) {
+		err = copy_from_user(addresses, addresses_user,
+				     sizeof(u64) * q->width);
 		if (err) {
 			err = -EFAULT;
 			goto err_syncs;
diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 281286f2b5f9..b8c1dd953665 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -1185,7 +1185,7 @@ static ssize_t setup_invalidate_state_cache_wa(struct xe_lrc *lrc,
 		return -ENOSPC;
 
 	*cmd++ = MI_LOAD_REGISTER_IMM | MI_LRI_NUM_REGS(1);
-	*cmd++ = CS_DEBUG_MODE1(0).addr;
+	*cmd++ = CS_DEBUG_MODE2(0).addr;
 	*cmd++ = _MASKED_BIT_ENABLE(INSTRUCTION_STATE_CACHE_INVALIDATE);
 
 	return cmd - batch;
diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c
index 33f4ac82fc80..6da42b2b5e46 100644
--- a/drivers/gpu/drm/xe/xe_nvm.c
+++ b/drivers/gpu/drm/xe/xe_nvm.c
@@ -83,6 +83,27 @@ static bool xe_nvm_writable_override(struct xe_device *xe)
 	return writable_override;
 }
 
+static void xe_nvm_fini(void *arg)
+{
+	struct xe_device *xe = arg;
+	struct intel_dg_nvm_dev *nvm = xe->nvm;
+
+	if (!xe->info.has_gsc_nvm)
+		return;
+
+	/* No access to internal NVM from VFs */
+	if (IS_SRIOV_VF(xe))
+		return;
+
+	/* Nvm pointer should not be NULL here */
+	if (WARN_ON(!nvm))
+		return;
+
+	auxiliary_device_delete(&nvm->aux_dev);
+	auxiliary_device_uninit(&nvm->aux_dev);
+	xe->nvm = NULL;
+}
+
 int xe_nvm_init(struct xe_device *xe)
 {
 	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
@@ -132,39 +153,17 @@ int xe_nvm_init(struct xe_device *xe)
 	ret = auxiliary_device_init(aux_dev);
 	if (ret) {
 		drm_err(&xe->drm, "xe-nvm aux init failed %d\n", ret);
-		goto err;
+		kfree(nvm);
+		xe->nvm = NULL;
+		return ret;
 	}
 
 	ret = auxiliary_device_add(aux_dev);
 	if (ret) {
 		drm_err(&xe->drm, "xe-nvm aux add failed %d\n", ret);
 		auxiliary_device_uninit(aux_dev);
-		goto err;
+		xe->nvm = NULL;
+		return ret;
 	}
-	return 0;
-
-err:
-	kfree(nvm);
-	xe->nvm = NULL;
-	return ret;
-}
-
-void xe_nvm_fini(struct xe_device *xe)
-{
-	struct intel_dg_nvm_dev *nvm = xe->nvm;
-
-	if (!xe->info.has_gsc_nvm)
-		return;
-
-	/* No access to internal NVM from VFs */
-	if (IS_SRIOV_VF(xe))
-		return;
-
-	/* Nvm pointer should not be NULL here */
-	if (WARN_ON(!nvm))
-		return;
-
-	auxiliary_device_delete(&nvm->aux_dev);
-	auxiliary_device_uninit(&nvm->aux_dev);
-	xe->nvm = NULL;
+	return devm_add_action_or_reset(xe->drm.dev, xe_nvm_fini, xe);
 }
diff --git a/drivers/gpu/drm/xe/xe_nvm.h b/drivers/gpu/drm/xe/xe_nvm.h
index 7f3d5f57bed0..fd3467ad35a4 100644
--- a/drivers/gpu/drm/xe/xe_nvm.h
+++ b/drivers/gpu/drm/xe/xe_nvm.h
@@ -10,6 +10,4 @@ struct xe_device;
 
 int xe_nvm_init(struct xe_device *xe);
 
-void xe_nvm_fini(struct xe_device *xe);
-
 #endif
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 9c9ea10d994c..2aa883f5ef79 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -342,7 +342,6 @@ static const struct xe_device_desc lnl_desc = {
 	.has_display = true,
 	.has_flat_ccs = 1,
 	.has_pxp = true,
-	.has_mem_copy_instr = true,
 	.max_gt_per_tile = 2,
 	.needs_scratch = true,
 	.va_bits = 48,
@@ -363,7 +362,6 @@ static const struct xe_device_desc bmg_desc = {
 	.has_heci_cscfi = 1,
 	.has_late_bind = true,
 	.has_sriov = true,
-	.has_mem_copy_instr = true,
 	.max_gt_per_tile = 2,
 	.needs_scratch = true,
 	.subplatforms = (const struct xe_subplatform_desc[]) {
@@ -380,7 +378,6 @@ static const struct xe_device_desc ptl_desc = {
 	.has_display = true,
 	.has_flat_ccs = 1,
 	.has_sriov = true,
-	.has_mem_copy_instr = true,
 	.max_gt_per_tile = 2,
 	.needs_scratch = true,
 	.needs_shared_vf_gt_wq = true,
@@ -393,7 +390,6 @@ static const struct xe_device_desc nvls_desc = {
 	.dma_mask_size = 46,
 	.has_display = true,
 	.has_flat_ccs = 1,
-	.has_mem_copy_instr = true,
 	.max_gt_per_tile = 2,
 	.require_force_probe = true,
 	.va_bits = 48,
@@ -675,7 +671,6 @@ static int xe_info_init_early(struct xe_device *xe,
 	xe->info.has_pxp = desc->has_pxp;
 	xe->info.has_sriov = xe_configfs_primary_gt_allowed(to_pci_dev(xe->drm.dev)) &&
 		desc->has_sriov;
-	xe->info.has_mem_copy_instr = desc->has_mem_copy_instr;
 	xe->info.skip_guc_pc = desc->skip_guc_pc;
 	xe->info.skip_mtcfg = desc->skip_mtcfg;
 	xe->info.skip_pcode = desc->skip_pcode;
@@ -864,6 +859,7 @@ static int xe_info_init(struct xe_device *xe,
 	xe->info.has_range_tlb_inval = graphics_desc->has_range_tlb_inval;
 	xe->info.has_usm = graphics_desc->has_usm;
 	xe->info.has_64bit_timestamp = graphics_desc->has_64bit_timestamp;
+	xe->info.has_mem_copy_instr = GRAPHICS_VER(xe) >= 20;
 
 	xe_info_probe_tile_count(xe);
 
diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h
index 9892c063a9c5..a4451bdc79fb 100644
--- a/drivers/gpu/drm/xe/xe_pci_types.h
+++ b/drivers/gpu/drm/xe/xe_pci_types.h
@@ -46,7 +46,6 @@ struct xe_device_desc {
 	u8 has_late_bind:1;
 	u8 has_llc:1;
 	u8 has_mbx_power_limits:1;
-	u8 has_mem_copy_instr:1;
 	u8 has_pxp:1;
 	u8 has_sriov:1;
 	u8 needs_scratch:1;