Merge tag 'drm-xe-fixes-2025-09-18' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

- Release kobject for the failure path (Shuicheng)
- SRIOV PF: Drop rounddown_pow_of_two fair (Michal)
- Remove type casting on hwmon (Mallesh)
- Defer free of NVM auxiliary container to device release (Nitin)
- Fix a NULL vs IS_ERR (Dan)
- Add cleanup action in xe_device_sysfs_init (Zongyao)
- Fix error handling if PXP fails to start (Daniele)
- Set GuC RCS/CCS yield policy (Daniele)

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://lore.kernel.org/r/aMwL7vxFP1L94IML@intel.com

17 files changed, 208 insertions, 73 deletions

diff --git a/drivers/gpu/drm/xe/abi/guc_actions_abi.h b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
index 81eb046aeebf..b9f67d7a00d8 100644
--- a/drivers/gpu/drm/xe/abi/guc_actions_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_actions_abi.h
@@ -117,6 +117,7 @@ enum xe_guc_action {
 	XE_GUC_ACTION_ENTER_S_STATE = 0x501,
 	XE_GUC_ACTION_EXIT_S_STATE = 0x502,
 	XE_GUC_ACTION_GLOBAL_SCHED_POLICY_CHANGE = 0x506,
+	XE_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV = 0x509,
 	XE_GUC_ACTION_SCHED_CONTEXT = 0x1000,
 	XE_GUC_ACTION_SCHED_CONTEXT_MODE_SET = 0x1001,
 	XE_GUC_ACTION_SCHED_CONTEXT_MODE_DONE = 0x1002,
diff --git a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
index 0366a9da5977..d7719d0e36ca 100644
--- a/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
+++ b/drivers/gpu/drm/xe/abi/guc_klvs_abi.h
@@ -17,6 +17,7 @@
  *  | 0 | 31:16 | **KEY** - KLV key identifier                                 |
  *  |   |       |   - `GuC Self Config KLVs`_                                  |
  *  |   |       |   - `GuC Opt In Feature KLVs`_                               |
+ *  |   |       |   - `GuC Scheduling Policies KLVs`_                          |
  *  |   |       |   - `GuC VGT Policy KLVs`_                                   |
  *  |   |       |   - `GuC VF Configuration KLVs`_                             |
  *  |   |       |                                                              |
@@ -153,6 +154,30 @@ enum  {
 #define GUC_KLV_OPT_IN_FEATURE_DYNAMIC_INHIBIT_CONTEXT_SWITCH_LEN 0u
 
 /**
+ * DOC: GuC Scheduling Policies KLVs
+ *
+ * `GuC KLV`_ keys available for use with UPDATE_SCHEDULING_POLICIES_KLV.
+ *
+ * _`GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD` : 0x1001
+ *      Some platforms do not allow concurrent execution of RCS and CCS
+ *      workloads from different address spaces. By default, the GuC prioritizes
+ *      RCS submissions over CCS ones, which can lead to CCS workloads being
+ *      significantly (or completely) starved of execution time. This KLV allows
+ *      the driver to specify a quantum (in ms) and a ratio (percentage value
+ *      between 0 and 100), and the GuC will prioritize the CCS for that
+ *      percentage of each quantum. For example, specifying 100ms and 30% will
+ *      make the GuC prioritize the CCS for 30ms of every 100ms.
+ *      Note that this does not necessarly mean that RCS and CCS engines will
+ *      only be active for their percentage of the quantum, as the restriction
+ *      only kicks in if both classes are fully busy with non-compatible address
+ *      spaces; i.e., if one engine is idle or running the same address space,
+ *      a pending job on the other engine will still be submitted to the HW no
+ *      matter what the ratio is
+ */
+#define GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD_KEY	0x1001
+#define GUC_KLV_SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD_LEN	2u
+
+/**
  * DOC: GuC VGT Policy KLVs
  *
  * `GuC KLV`_ keys available for use with PF2GUC_UPDATE_VGT_POLICY.
diff --git a/drivers/gpu/drm/xe/xe_device_sysfs.c b/drivers/gpu/drm/xe/xe_device_sysfs.c
index bd9015761aa0..3e3b2d9033a7 100644
--- a/drivers/gpu/drm/xe/xe_device_sysfs.c
+++ b/drivers/gpu/drm/xe/xe_device_sysfs.c
@@ -311,12 +311,16 @@ int xe_device_sysfs_init(struct xe_device *xe)
 	if (xe->info.platform == XE_BATTLEMAGE) {
 		ret = sysfs_create_files(&dev->kobj, auto_link_downgrade_attrs);
 		if (ret)
-			return ret;
+			goto cleanup;
 
 		ret = late_bind_create_files(dev);
 		if (ret)
-			return ret;
+			goto cleanup;
 	}
 
 	return devm_add_action_or_reset(dev, xe_device_sysfs_fini, xe);
+
+cleanup:
+	xe_device_sysfs_fini(xe);
+	return ret;
 }
diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
index 8991b4aed440..c07edcda99c5 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue.c
+++ b/drivers/gpu/drm/xe/xe_exec_queue.c
@@ -151,6 +151,16 @@ err_lrc:
 	return err;
 }
 
+static void __xe_exec_queue_fini(struct xe_exec_queue *q)
+{
+	int i;
+
+	q->ops->fini(q);
+
+	for (i = 0; i < q->width; ++i)
+		xe_lrc_put(q->lrc[i]);
+}
+
 struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *vm,
 					   u32 logical_mask, u16 width,
 					   struct xe_hw_engine *hwe, u32 flags,
@@ -181,11 +191,13 @@ struct xe_exec_queue *xe_exec_queue_create(struct xe_device *xe, struct xe_vm *v
 	if (xe_exec_queue_uses_pxp(q)) {
 		err = xe_pxp_exec_queue_add(xe->pxp, q);
 		if (err)
-			goto err_post_alloc;
+			goto err_post_init;
 	}
 
 	return q;
 
+err_post_init:
+	__xe_exec_queue_fini(q);
 err_post_alloc:
 	__xe_exec_queue_free(q);
 	return ERR_PTR(err);
@@ -283,13 +295,11 @@ void xe_exec_queue_destroy(struct kref *ref)
 			xe_exec_queue_put(eq);
 	}
 
-	q->ops->fini(q);
+	q->ops->destroy(q);
 }
 
 void xe_exec_queue_fini(struct xe_exec_queue *q)
 {
-	int i;
-
 	/*
 	 * Before releasing our ref to lrc and xef, accumulate our run ticks
 	 * and wakeup any waiters.
@@ -298,9 +308,7 @@ void xe_exec_queue_fini(struct xe_exec_queue *q)
 	if (q->xef && atomic_dec_and_test(&q->xef->exec_queue.pending_removal))
 		wake_up_var(&q->xef->exec_queue.pending_removal);
 
-	for (i = 0; i < q->width; ++i)
-		xe_lrc_put(q->lrc[i]);
-
+	__xe_exec_queue_fini(q);
 	__xe_exec_queue_free(q);
 }
 
diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
index cc1cffb5c87f..1c9d03f2a3e5 100644
--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
@@ -166,8 +166,14 @@ struct xe_exec_queue_ops {
 	int (*init)(struct xe_exec_queue *q);
 	/** @kill: Kill inflight submissions for backend */
 	void (*kill)(struct xe_exec_queue *q);
-	/** @fini: Fini exec queue for submission backend */
+	/** @fini: Undoes the init() for submission backend */
 	void (*fini)(struct xe_exec_queue *q);
+	/**
+	 * @destroy: Destroy exec queue for submission backend. The backend
+	 * function must call xe_exec_queue_fini() (which will in turn call the
+	 * fini() backend function) to ensure the queue is properly cleaned up.
+	 */
+	void (*destroy)(struct xe_exec_queue *q);
 	/** @set_priority: Set priority for exec queue */
 	int (*set_priority)(struct xe_exec_queue *q,
 			    enum xe_exec_queue_priority priority);
diff --git a/drivers/gpu/drm/xe/xe_execlist.c b/drivers/gpu/drm/xe/xe_execlist.c
index 788f56b066b6..f83d421ac9d3 100644
--- a/drivers/gpu/drm/xe/xe_execlist.c
+++ b/drivers/gpu/drm/xe/xe_execlist.c
@@ -385,10 +385,20 @@ err_free:
 	return err;
 }
 
-static void execlist_exec_queue_fini_async(struct work_struct *w)
+static void execlist_exec_queue_fini(struct xe_exec_queue *q)
+{
+	struct xe_execlist_exec_queue *exl = q->execlist;
+
+	drm_sched_entity_fini(&exl->entity);
+	drm_sched_fini(&exl->sched);
+
+	kfree(exl);
+}
+
+static void execlist_exec_queue_destroy_async(struct work_struct *w)
 {
 	struct xe_execlist_exec_queue *ee =
-		container_of(w, struct xe_execlist_exec_queue, fini_async);
+		container_of(w, struct xe_execlist_exec_queue, destroy_async);
 	struct xe_exec_queue *q = ee->q;
 	struct xe_execlist_exec_queue *exl = q->execlist;
 	struct xe_device *xe = gt_to_xe(q->gt);
@@ -401,10 +411,6 @@ static void execlist_exec_queue_fini_async(struct work_struct *w)
 		list_del(&exl->active_link);
 	spin_unlock_irqrestore(&exl->port->lock, flags);
 
-	drm_sched_entity_fini(&exl->entity);
-	drm_sched_fini(&exl->sched);
-	kfree(exl);
-
 	xe_exec_queue_fini(q);
 }
 
@@ -413,10 +419,10 @@ static void execlist_exec_queue_kill(struct xe_exec_queue *q)
 	/* NIY */
 }
 
-static void execlist_exec_queue_fini(struct xe_exec_queue *q)
+static void execlist_exec_queue_destroy(struct xe_exec_queue *q)
 {
-	INIT_WORK(&q->execlist->fini_async, execlist_exec_queue_fini_async);
-	queue_work(system_unbound_wq, &q->execlist->fini_async);
+	INIT_WORK(&q->execlist->destroy_async, execlist_exec_queue_destroy_async);
+	queue_work(system_unbound_wq, &q->execlist->destroy_async);
 }
 
 static int execlist_exec_queue_set_priority(struct xe_exec_queue *q,
@@ -467,6 +473,7 @@ static const struct xe_exec_queue_ops execlist_exec_queue_ops = {
 	.init = execlist_exec_queue_init,
 	.kill = execlist_exec_queue_kill,
 	.fini = execlist_exec_queue_fini,
+	.destroy = execlist_exec_queue_destroy,
 	.set_priority = execlist_exec_queue_set_priority,
 	.set_timeslice = execlist_exec_queue_set_timeslice,
 	.set_preempt_timeout = execlist_exec_queue_set_preempt_timeout,
diff --git a/drivers/gpu/drm/xe/xe_execlist_types.h b/drivers/gpu/drm/xe/xe_execlist_types.h
index 415140936f11..92c4ba52db0c 100644
--- a/drivers/gpu/drm/xe/xe_execlist_types.h
+++ b/drivers/gpu/drm/xe/xe_execlist_types.h
@@ -42,7 +42,7 @@ struct xe_execlist_exec_queue {
 
 	bool has_run;
 
-	struct work_struct fini_async;
+	struct work_struct destroy_async;
 
 	enum xe_exec_queue_priority active_priority;
 	struct list_head active_link;
diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index c8eda36546d3..17634195cdc2 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -41,6 +41,7 @@
 #include "xe_gt_topology.h"
 #include "xe_guc_exec_queue_types.h"
 #include "xe_guc_pc.h"
+#include "xe_guc_submit.h"
 #include "xe_hw_fence.h"
 #include "xe_hw_engine_class_sysfs.h"
 #include "xe_irq.h"
@@ -97,7 +98,7 @@ void xe_gt_sanitize(struct xe_gt *gt)
 	 * FIXME: if xe_uc_sanitize is called here, on TGL driver will not
 	 * reload
 	 */
-	gt->uc.guc.submission_state.enabled = false;
+	xe_guc_submit_disable(&gt->uc.guc);
 }
 
 static void xe_gt_enable_host_l2_vram(struct xe_gt *gt)
diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
index 494909f74eb2..d84831a03610 100644
--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
@@ -1632,7 +1632,6 @@ static u64 pf_estimate_fair_lmem(struct xe_gt *gt, unsigned int num_vfs)
 	u64 fair;
 
 	fair = div_u64(available, num_vfs);
-	fair = rounddown_pow_of_two(fair);	/* XXX: ttm_vram_mgr & drm_buddy limitation */
 	fair = ALIGN_DOWN(fair, alignment);
 #ifdef MAX_FAIR_LMEM
 	fair = min_t(u64, MAX_FAIR_LMEM, fair);
diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
index b1d1d6da3758..270fc3792493 100644
--- a/drivers/gpu/drm/xe/xe_guc.c
+++ b/drivers/gpu/drm/xe/xe_guc.c
@@ -880,9 +880,7 @@ int xe_guc_post_load_init(struct xe_guc *guc)
 			return ret;
 	}
 
-	guc->submission_state.enabled = true;
-
-	return 0;
+	return xe_guc_submit_enable(guc);
 }
 
 int xe_guc_reset(struct xe_guc *guc)
@@ -1579,7 +1577,7 @@ void xe_guc_sanitize(struct xe_guc *guc)
 {
 	xe_uc_fw_sanitize(&guc->fw);
 	xe_guc_ct_disable(&guc->ct);
-	guc->submission_state.enabled = false;
+	xe_guc_submit_disable(guc);
 }
 
 int xe_guc_reset_prepare(struct xe_guc *guc)
diff --git a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h
index a3f421e2adc0..c30c0e3ccbbb 100644
--- a/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_exec_queue_types.h
@@ -35,8 +35,8 @@ struct xe_guc_exec_queue {
 	struct xe_sched_msg static_msgs[MAX_STATIC_MSG_TYPE];
 	/** @lr_tdr: long running TDR worker */
 	struct work_struct lr_tdr;
-	/** @fini_async: do final fini async from this worker */
-	struct work_struct fini_async;
+	/** @destroy_async: do final destroy async from this worker */
+	struct work_struct destroy_async;
 	/** @resume_time: time of last resume */
 	u64 resume_time;
 	/** @state: GuC specific state for this xe_exec_queue */
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index cafb47711e9b..0104afbc941c 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -32,6 +32,7 @@
 #include "xe_guc_ct.h"
 #include "xe_guc_exec_queue_types.h"
 #include "xe_guc_id_mgr.h"
+#include "xe_guc_klv_helpers.h"
 #include "xe_guc_submit_types.h"
 #include "xe_hw_engine.h"
 #include "xe_hw_fence.h"
@@ -316,6 +317,71 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids)
 	return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc);
 }
 
+/*
+ * Given that we want to guarantee enough RCS throughput to avoid missing
+ * frames, we set the yield policy to 20% of each 80ms interval.
+ */
+#define RC_YIELD_DURATION	80	/* in ms */
+#define RC_YIELD_RATIO		20	/* in percent */
+static u32 *emit_render_compute_yield_klv(u32 *emit)
+{
+	*emit++ = PREP_GUC_KLV_TAG(SCHEDULING_POLICIES_RENDER_COMPUTE_YIELD);
+	*emit++ = RC_YIELD_DURATION;
+	*emit++ = RC_YIELD_RATIO;
+
+	return emit;
+}
+
+#define SCHEDULING_POLICY_MAX_DWORDS 16
+static int guc_init_global_schedule_policy(struct xe_guc *guc)
+{
+	u32 data[SCHEDULING_POLICY_MAX_DWORDS];
+	u32 *emit = data;
+	u32 count = 0;
+	int ret;
+
+	if (GUC_SUBMIT_VER(guc) < MAKE_GUC_VER(1, 1, 0))
+		return 0;
+
+	*emit++ = XE_GUC_ACTION_UPDATE_SCHEDULING_POLICIES_KLV;
+
+	if (CCS_MASK(guc_to_gt(guc)))
+		emit = emit_render_compute_yield_klv(emit);
+
+	count = emit - data;
+	if (count > 1) {
+		xe_assert(guc_to_xe(guc), count <= SCHEDULING_POLICY_MAX_DWORDS);
+
+		ret = xe_guc_ct_send_block(&guc->ct, data, count);
+		if (ret < 0) {
+			xe_gt_err(guc_to_gt(guc),
+				  "failed to enable GuC sheduling policies: %pe\n",
+				  ERR_PTR(ret));
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+int xe_guc_submit_enable(struct xe_guc *guc)
+{
+	int ret;
+
+	ret = guc_init_global_schedule_policy(guc);
+	if (ret)
+		return ret;
+
+	guc->submission_state.enabled = true;
+
+	return 0;
+}
+
+void xe_guc_submit_disable(struct xe_guc *guc)
+{
+	guc->submission_state.enabled = false;
+}
+
 static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa_count)
 {
 	int i;
@@ -1277,48 +1343,57 @@ rearm:
 	return DRM_GPU_SCHED_STAT_NO_HANG;
 }
 
-static void __guc_exec_queue_fini_async(struct work_struct *w)
+static void guc_exec_queue_fini(struct xe_exec_queue *q)
+{
+	struct xe_guc_exec_queue *ge = q->guc;
+	struct xe_guc *guc = exec_queue_to_guc(q);
+
+	release_guc_id(guc, q);
+	xe_sched_entity_fini(&ge->entity);
+	xe_sched_fini(&ge->sched);
+
+	/*
+	 * RCU free due sched being exported via DRM scheduler fences
+	 * (timeline name).
+	 */
+	kfree_rcu(ge, rcu);
+}
+
+static void __guc_exec_queue_destroy_async(struct work_struct *w)
 {
 	struct xe_guc_exec_queue *ge =
-		container_of(w, struct xe_guc_exec_queue, fini_async);
+		container_of(w, struct xe_guc_exec_queue, destroy_async);
 	struct xe_exec_queue *q = ge->q;
 	struct xe_guc *guc = exec_queue_to_guc(q);
 
 	xe_pm_runtime_get(guc_to_xe(guc));
 	trace_xe_exec_queue_destroy(q);
 
-	release_guc_id(guc, q);
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
 	/* Confirm no work left behind accessing device structures */
 	cancel_delayed_work_sync(&ge->sched.base.work_tdr);
-	xe_sched_entity_fini(&ge->entity);
-	xe_sched_fini(&ge->sched);
 
-	/*
-	 * RCU free due sched being exported via DRM scheduler fences
-	 * (timeline name).
-	 */
-	kfree_rcu(ge, rcu);
 	xe_exec_queue_fini(q);
+
 	xe_pm_runtime_put(guc_to_xe(guc));
 }
 
-static void guc_exec_queue_fini_async(struct xe_exec_queue *q)
+static void guc_exec_queue_destroy_async(struct xe_exec_queue *q)
 {
 	struct xe_guc *guc = exec_queue_to_guc(q);
 	struct xe_device *xe = guc_to_xe(guc);
 
-	INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async);
+	INIT_WORK(&q->guc->destroy_async, __guc_exec_queue_destroy_async);
 
 	/* We must block on kernel engines so slabs are empty on driver unload */
 	if (q->flags & EXEC_QUEUE_FLAG_PERMANENT || exec_queue_wedged(q))
-		__guc_exec_queue_fini_async(&q->guc->fini_async);
+		__guc_exec_queue_destroy_async(&q->guc->destroy_async);
 	else
-		queue_work(xe->destroy_wq, &q->guc->fini_async);
+		queue_work(xe->destroy_wq, &q->guc->destroy_async);
 }
 
-static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q)
+static void __guc_exec_queue_destroy(struct xe_guc *guc, struct xe_exec_queue *q)
 {
 	/*
 	 * Might be done from within the GPU scheduler, need to do async as we
@@ -1327,7 +1402,7 @@ static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q)
 	 * this we and don't really care when everything is fini'd, just that it
 	 * is.
 	 */
-	guc_exec_queue_fini_async(q);
+	guc_exec_queue_destroy_async(q);
 }
 
 static void __guc_exec_queue_process_msg_cleanup(struct xe_sched_msg *msg)
@@ -1341,7 +1416,7 @@ static void __guc_exec_queue_process_msg_cleanup(struct xe_sched_msg *msg)
 	if (exec_queue_registered(q))
 		disable_scheduling_deregister(guc, q);
 	else
-		__guc_exec_queue_fini(guc, q);
+		__guc_exec_queue_destroy(guc, q);
 }
 
 static bool guc_exec_queue_allowed_to_change_state(struct xe_exec_queue *q)
@@ -1574,14 +1649,14 @@ static bool guc_exec_queue_try_add_msg(struct xe_exec_queue *q,
 #define STATIC_MSG_CLEANUP	0
 #define STATIC_MSG_SUSPEND	1
 #define STATIC_MSG_RESUME	2
-static void guc_exec_queue_fini(struct xe_exec_queue *q)
+static void guc_exec_queue_destroy(struct xe_exec_queue *q)
 {
 	struct xe_sched_msg *msg = q->guc->static_msgs + STATIC_MSG_CLEANUP;
 
 	if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && !exec_queue_wedged(q))
 		guc_exec_queue_add_msg(q, msg, CLEANUP);
 	else
-		__guc_exec_queue_fini(exec_queue_to_guc(q), q);
+		__guc_exec_queue_destroy(exec_queue_to_guc(q), q);
 }
 
 static int guc_exec_queue_set_priority(struct xe_exec_queue *q,
@@ -1711,6 +1786,7 @@ static const struct xe_exec_queue_ops guc_exec_queue_ops = {
 	.init = guc_exec_queue_init,
 	.kill = guc_exec_queue_kill,
 	.fini = guc_exec_queue_fini,
+	.destroy = guc_exec_queue_destroy,
 	.set_priority = guc_exec_queue_set_priority,
 	.set_timeslice = guc_exec_queue_set_timeslice,
 	.set_preempt_timeout = guc_exec_queue_set_preempt_timeout,
@@ -1732,7 +1808,7 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
 		if (exec_queue_extra_ref(q) || xe_exec_queue_is_lr(q))
 			xe_exec_queue_put(q);
 		else if (exec_queue_destroyed(q))
-			__guc_exec_queue_fini(guc, q);
+			__guc_exec_queue_destroy(guc, q);
 	}
 	if (q->guc->suspend_pending) {
 		set_exec_queue_suspended(q);
@@ -1989,7 +2065,7 @@ static void handle_deregister_done(struct xe_guc *guc, struct xe_exec_queue *q)
 	if (exec_queue_extra_ref(q) || xe_exec_queue_is_lr(q))
 		xe_exec_queue_put(q);
 	else
-		__guc_exec_queue_fini(guc, q);
+		__guc_exec_queue_destroy(guc, q);
 }
 
 int xe_guc_deregister_done_handler(struct xe_guc *guc, u32 *msg, u32 len)
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h
index 9b71a986c6ca..0d126b807c10 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.h
+++ b/drivers/gpu/drm/xe/xe_guc_submit.h
@@ -13,6 +13,8 @@ struct xe_exec_queue;
 struct xe_guc;
 
 int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids);
+int xe_guc_submit_enable(struct xe_guc *guc);
+void xe_guc_submit_disable(struct xe_guc *guc);
 
 int xe_guc_submit_reset_prepare(struct xe_guc *guc);
 void xe_guc_submit_reset_wait(struct xe_guc *guc);
diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
index c17ed1ae8649..c5b63e10bb91 100644
--- a/drivers/gpu/drm/xe/xe_hwmon.c
+++ b/drivers/gpu/drm/xe/xe_hwmon.c
@@ -286,7 +286,7 @@ static struct xe_reg xe_hwmon_get_reg(struct xe_hwmon *hwmon, enum xe_hwmon_reg
  */
 static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channel, long *value)
 {
-	u64 reg_val = 0, min, max;
+	u32 reg_val = 0;
 	struct xe_device *xe = hwmon->xe;
 	struct xe_reg rapl_limit, pkg_power_sku;
 	struct xe_mmio *mmio = xe_root_tile_mmio(xe);
@@ -294,7 +294,7 @@ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channe
 	mutex_lock(&hwmon->hwmon_lock);
 
 	if (hwmon->xe->info.has_mbx_power_limits) {
-		xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, (u32 *)&reg_val);
+		xe_hwmon_pcode_read_power_limit(hwmon, attr, channel, &reg_val);
 	} else {
 		rapl_limit = xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel);
 		pkg_power_sku = xe_hwmon_get_reg(hwmon, REG_PKG_POWER_SKU, channel);
@@ -304,19 +304,21 @@ static void xe_hwmon_power_max_read(struct xe_hwmon *hwmon, u32 attr, int channe
 	/* Check if PL limits are disabled. */
 	if (!(reg_val & PWR_LIM_EN)) {
 		*value = PL_DISABLE;
-		drm_info(&hwmon->xe->drm, "%s disabled for channel %d, val 0x%016llx\n",
+		drm_info(&hwmon->xe->drm, "%s disabled for channel %d, val 0x%08x\n",
 			 PWR_ATTR_TO_STR(attr), channel, reg_val);
 		goto unlock;
 	}
 
 	reg_val = REG_FIELD_GET(PWR_LIM_VAL, reg_val);
-	*value = mul_u64_u32_shr(reg_val, SF_POWER, hwmon->scl_shift_power);
+	*value = mul_u32_u32(reg_val, SF_POWER) >> hwmon->scl_shift_power;
 
 	/* For platforms with mailbox power limit support clamping would be done by pcode. */
 	if (!hwmon->xe->info.has_mbx_power_limits) {
-		reg_val = xe_mmio_read64_2x32(mmio, pkg_power_sku);
-		min = REG_FIELD_GET(PKG_MIN_PWR, reg_val);
-		max = REG_FIELD_GET(PKG_MAX_PWR, reg_val);
+		u64 pkg_pwr, min, max;
+
+		pkg_pwr = xe_mmio_read64_2x32(mmio, pkg_power_sku);
+		min = REG_FIELD_GET(PKG_MIN_PWR, pkg_pwr);
+		max = REG_FIELD_GET(PKG_MAX_PWR, pkg_pwr);
 		min = mul_u64_u32_shr(min, SF_POWER, hwmon->scl_shift_power);
 		max = mul_u64_u32_shr(max, SF_POWER, hwmon->scl_shift_power);
 		if (min && max)
@@ -493,8 +495,8 @@ xe_hwmon_power_max_interval_show(struct device *dev, struct device_attribute *at
 {
 	struct xe_hwmon *hwmon = dev_get_drvdata(dev);
 	struct xe_mmio *mmio = xe_root_tile_mmio(hwmon->xe);
-	u32 x, y, x_w = 2; /* 2 bits */
-	u64 r, tau4, out;
+	u32 reg_val, x, y, x_w = 2; /* 2 bits */
+	u64 tau4, out;
 	int channel = (to_sensor_dev_attr(attr)->index % 2) ? CHANNEL_PKG : CHANNEL_CARD;
 	u32 power_attr = (to_sensor_dev_attr(attr)->index > 1) ? PL2_HWMON_ATTR : PL1_HWMON_ATTR;
 
@@ -505,23 +507,24 @@ xe_hwmon_power_max_interval_show(struct device *dev, struct device_attribute *at
 	mutex_lock(&hwmon->hwmon_lock);
 
 	if (hwmon->xe->info.has_mbx_power_limits) {
-		ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, (u32 *)&r);
+		ret = xe_hwmon_pcode_read_power_limit(hwmon, power_attr, channel, &reg_val);
 		if (ret) {
 			drm_err(&hwmon->xe->drm,
-				"power interval read fail, ch %d, attr %d, r 0%llx, ret %d\n",
-				channel, power_attr, r, ret);
-			r = 0;
+				"power interval read fail, ch %d, attr %d, val 0x%08x, ret %d\n",
+				channel, power_attr, reg_val, ret);
+			reg_val = 0;
 		}
 	} else {
-		r = xe_mmio_read32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT, channel));
+		reg_val = xe_mmio_read32(mmio, xe_hwmon_get_reg(hwmon, REG_PKG_RAPL_LIMIT,
+								channel));
 	}
 
 	mutex_unlock(&hwmon->hwmon_lock);
 
 	xe_pm_runtime_put(hwmon->xe);
 
-	x = REG_FIELD_GET(PWR_LIM_TIME_X, r);
-	y = REG_FIELD_GET(PWR_LIM_TIME_Y, r);
+	x = REG_FIELD_GET(PWR_LIM_TIME_X, reg_val);
+	y = REG_FIELD_GET(PWR_LIM_TIME_Y, reg_val);
 
 	/*
 	 * tau = (1 + (x / 4)) * power(2,y), x = bits(23:22), y = bits(21:17)
diff --git a/drivers/gpu/drm/xe/xe_nvm.c b/drivers/gpu/drm/xe/xe_nvm.c
index 61b0a1531a53..2cfe9eb67391 100644
--- a/drivers/gpu/drm/xe/xe_nvm.c
+++ b/drivers/gpu/drm/xe/xe_nvm.c
@@ -35,6 +35,10 @@ static const struct intel_dg_nvm_region regions[INTEL_DG_NVM_REGIONS] = {
 
 static void xe_nvm_release_dev(struct device *dev)
 {
+	struct auxiliary_device *aux = container_of(dev, struct auxiliary_device, dev);
+	struct intel_dg_nvm_dev *nvm = container_of(aux, struct intel_dg_nvm_dev, aux_dev);
+
+	kfree(nvm);
 }
 
 static bool xe_nvm_non_posted_erase(struct xe_device *xe)
@@ -162,6 +166,5 @@ void xe_nvm_fini(struct xe_device *xe)
 
 	auxiliary_device_delete(&nvm->aux_dev);
 	auxiliary_device_uninit(&nvm->aux_dev);
-	kfree(nvm);
 	xe->nvm = NULL;
 }
diff --git a/drivers/gpu/drm/xe/xe_tile_sysfs.c b/drivers/gpu/drm/xe/xe_tile_sysfs.c
index b804234a6551..9e1236a9ec67 100644
--- a/drivers/gpu/drm/xe/xe_tile_sysfs.c
+++ b/drivers/gpu/drm/xe/xe_tile_sysfs.c
@@ -44,16 +44,18 @@ int xe_tile_sysfs_init(struct xe_tile *tile)
 	kt->tile = tile;
 
 	err = kobject_add(&kt->base, &dev->kobj, "tile%d", tile->id);
-	if (err) {
-		kobject_put(&kt->base);
-		return err;
-	}
+	if (err)
+		goto err_object;
 
 	tile->sysfs = &kt->base;
 
 	err = xe_vram_freq_sysfs_init(tile);
 	if (err)
-		return err;
+		goto err_object;
 
 	return devm_add_action_or_reset(xe->drm.dev, tile_sysfs_fini, tile);
+
+err_object:
+	kobject_put(&kt->base);
+	return err;
 }
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index dc4f61e56579..5146999d27fa 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -240,8 +240,8 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
 
 	pfence = xe_preempt_fence_create(q, q->lr.context,
 					 ++q->lr.seqno);
-	if (!pfence) {
-		err = -ENOMEM;
+	if (IS_ERR(pfence)) {
+		err = PTR_ERR(pfence);
 		goto out_fini;
 	}