Merge tag 'drm-xe-next-fixes-2025-06-05' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-next

Driver Changes:
- A couple of vm init fixes (Matt Auld)
- Hwmon fixes (Karthik)
- Drop reduntant conversion to bool (Raag)
- Fix CONFIG_INTEL_VSEC dependency (Arnd)
- Rework eviction rejection of bound external bos (Thomas)
- Stop re-submitting signalled jobs (Matt Auld)
- A couple of pxp fixes (Daniele)
- Add back a fix that got lost in a merge (Matt Auld)
- Create LRC bo without VM (Niranjana)
- Fix for the above fix (Maciej)

Signed-off-by: Dave Airlie <[email protected]>

From: Thomas Hellstrom <[email protected]>
Link: https://lore.kernel.org/r/aEHq44uIAZwfK-mG@fedora

Author: airlied

Documentation/ABI/testing/sysfs-driver-intel-xe-hwmon

@@ -60,26 +60,26 @@ Description:	RO. Package default power limit (default TDP setting).
 
 		Only supported for particular Intel Xe graphics platforms.
 
-What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power2_crit
-Date:		February 2024
-KernelVersion:	6.8
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/power1_crit
+Date:		May 2025
+KernelVersion:	6.15
 Contact:	[email protected]
-Description:	RW. Package reactive critical (I1) power limit in microwatts.
+Description:	RW. Card reactive critical (I1) power limit in microwatts.
 
-		Package reactive critical (I1) power limit in microwatts is exposed
+		Card reactive critical (I1) power limit in microwatts is exposed
 		for client products. The power controller will throttle the
 		operating frequency if the power averaged over a window exceeds
 		this limit.
 
 		Only supported for particular Intel Xe graphics platforms.
 
-What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/curr2_crit
-Date:		February 2024
-KernelVersion:	6.8
+What:		/sys/bus/pci/drivers/xe/.../hwmon/hwmon<i>/curr1_crit
+Date:		May 2025
+KernelVersion:	6.15
 Contact:	[email protected]
-Description:	RW. Package reactive critical (I1) power limit in milliamperes.
+Description:	RW. Card reactive critical (I1) power limit in milliamperes.
 
-		Package reactive critical (I1) power limit in milliamperes is
+		Card reactive critical (I1) power limit in milliamperes is
 		exposed for server products. The power controller will throttle
 		the operating frequency if the power averaged over a window
 		exceeds this limit.

drivers/gpu/drm/xe/Kconfig

@@ -2,6 +2,8 @@
 config DRM_XE
 	tristate "Intel Xe Graphics"
 	depends on DRM && PCI && MMU && (m || (y && KUNIT=y))
+	depends on INTEL_VSEC || !INTEL_VSEC
+	depends on X86_PLATFORM_DEVICES || !(X86 && ACPI)
 	select INTERVAL_TREE
 	# we need shmfs for the swappable backing store, and in particular
 	# the shmem_readpage() which depends upon tmpfs
@@ -27,7 +29,6 @@ config DRM_XE
 	select BACKLIGHT_CLASS_DEVICE if ACPI
 	select INPUT if ACPI
 	select ACPI_VIDEO if X86 && ACPI
-	select X86_PLATFORM_DEVICES if X86 && ACPI
 	select ACPI_WMI if X86 && ACPI
 	select SYNC_FILE
 	select IOSF_MBI

drivers/gpu/drm/xe/regs/xe_mchbar_regs.h

@@ -38,10 +38,10 @@
 #define   TEMP_MASK				REG_GENMASK(7, 0)
 
 #define PCU_CR_PACKAGE_RAPL_LIMIT		XE_REG(MCHBAR_MIRROR_BASE_SNB + 0x59a0)
-#define   PKG_PWR_LIM_1				REG_GENMASK(14, 0)
-#define   PKG_PWR_LIM_1_EN			REG_BIT(15)
-#define   PKG_PWR_LIM_1_TIME			REG_GENMASK(23, 17)
-#define   PKG_PWR_LIM_1_TIME_X			REG_GENMASK(23, 22)
-#define   PKG_PWR_LIM_1_TIME_Y			REG_GENMASK(21, 17)
+#define   PWR_LIM_VAL				REG_GENMASK(14, 0)
+#define   PWR_LIM_EN				REG_BIT(15)
+#define   PWR_LIM_TIME				REG_GENMASK(23, 17)
+#define   PWR_LIM_TIME_X			REG_GENMASK(23, 22)
+#define   PWR_LIM_TIME_Y			REG_GENMASK(21, 17)
 
 #endif /* _XE_MCHBAR_REGS_H_ */

drivers/gpu/drm/xe/regs/xe_pcode_regs.h

@@ -18,16 +18,12 @@
 #define PVC_GT0_PLATFORM_ENERGY_STATUS          XE_REG(0x28106c)
 #define PVC_GT0_PACKAGE_POWER_SKU               XE_REG(0x281080)
 
-#define BMG_PACKAGE_POWER_SKU			XE_REG(0x138098)
-#define BMG_PACKAGE_POWER_SKU_UNIT		XE_REG(0x1380dc)
 #define BMG_PACKAGE_ENERGY_STATUS		XE_REG(0x138120)
 #define BMG_FAN_1_SPEED				XE_REG(0x138140)
 #define BMG_FAN_2_SPEED				XE_REG(0x138170)
 #define BMG_FAN_3_SPEED				XE_REG(0x1381a0)
 #define BMG_VRAM_TEMPERATURE			XE_REG(0x1382c0)
 #define BMG_PACKAGE_TEMPERATURE			XE_REG(0x138434)
-#define BMG_PACKAGE_RAPL_LIMIT			XE_REG(0x138440)
 #define BMG_PLATFORM_ENERGY_STATUS		XE_REG(0x138458)
-#define BMG_PLATFORM_POWER_LIMIT		XE_REG(0x138460)
 
 #endif /* _XE_PCODE_REGS_H_ */

drivers/gpu/drm/xe/xe_bo.c

@@ -841,21 +841,6 @@ static int xe_bo_move(struct ttm_buffer_object *ttm_bo, bool evict,
 		goto out;
 	}
 
-	/* Reject BO eviction if BO is bound to current VM. */
-	if (evict && ctx->resv) {
-		struct drm_gpuvm_bo *vm_bo;
-
-		drm_gem_for_each_gpuvm_bo(vm_bo, &bo->ttm.base) {
-			struct xe_vm *vm = gpuvm_to_vm(vm_bo->vm);
-
-			if (xe_vm_resv(vm) == ctx->resv &&
-			    xe_vm_in_preempt_fence_mode(vm)) {
-				ret = -EBUSY;
-				goto out;
-			}
-		}
-	}
-
 	/*
 	 * Failed multi-hop where the old_mem is still marked as
 	 * TTM_PL_FLAG_TEMPORARY, should just be a dummy move.
@@ -1013,6 +998,25 @@ static long xe_bo_shrink_purge(struct ttm_operation_ctx *ctx,
 	return lret;
 }
 
+static bool
+xe_bo_eviction_valuable(struct ttm_buffer_object *bo, const struct ttm_place *place)
+{
+	struct drm_gpuvm_bo *vm_bo;
+
+	if (!ttm_bo_eviction_valuable(bo, place))
+		return false;
+
+	if (!xe_bo_is_xe_bo(bo))
+		return true;
+
+	drm_gem_for_each_gpuvm_bo(vm_bo, &bo->base) {
+		if (xe_vm_is_validating(gpuvm_to_vm(vm_bo->vm)))
+			return false;
+	}
+
+	return true;
+}
+
 /**
  * xe_bo_shrink() - Try to shrink an xe bo.
  * @ctx: The struct ttm_operation_ctx used for shrinking.
@@ -1047,7 +1051,7 @@ long xe_bo_shrink(struct ttm_operation_ctx *ctx, struct ttm_buffer_object *bo,
 	    (flags.purge && !xe_tt->purgeable))
 		return -EBUSY;
 
-	if (!ttm_bo_eviction_valuable(bo, &place))
+	if (!xe_bo_eviction_valuable(bo, &place))
 		return -EBUSY;
 
 	if (!xe_bo_is_xe_bo(bo) || !xe_bo_get_unless_zero(xe_bo))
@@ -1588,7 +1592,7 @@ const struct ttm_device_funcs xe_ttm_funcs = {
 	.io_mem_pfn = xe_ttm_io_mem_pfn,
 	.access_memory = xe_ttm_access_memory,
 	.release_notify = xe_ttm_bo_release_notify,
-	.eviction_valuable = ttm_bo_eviction_valuable,
+	.eviction_valuable = xe_bo_eviction_valuable,
 	.delete_mem_notify = xe_ttm_bo_delete_mem_notify,
 	.swap_notify = xe_ttm_bo_swap_notify,
 };
@@ -2431,6 +2435,8 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
 		.no_wait_gpu = false,
 		.gfp_retry_mayfail = true,
 	};
+	struct pin_cookie cookie;
+	int ret;
 
 	if (vm) {
 		lockdep_assert_held(&vm->lock);
@@ -2440,8 +2446,12 @@ int xe_bo_validate(struct xe_bo *bo, struct xe_vm *vm, bool allow_res_evict)
 		ctx.resv = xe_vm_resv(vm);
 	}
 
+	cookie = xe_vm_set_validating(vm, allow_res_evict);
 	trace_xe_bo_validate(bo);
-	return ttm_bo_validate(&bo->ttm, &bo->placement, &ctx);
+	ret = ttm_bo_validate(&bo->ttm, &bo->placement, &ctx);
+	xe_vm_clear_validating(vm, allow_res_evict, cookie);
+
+	return ret;
 }
 
 bool xe_bo_is_xe_bo(struct ttm_buffer_object *bo)
@@ -2557,7 +2567,7 @@ typedef int (*xe_gem_create_set_property_fn)(struct xe_device *xe,
 					     u64 value);
 
 static const xe_gem_create_set_property_fn gem_create_set_property_funcs[] = {
-	[DRM_XE_GEM_CREATE_EXTENSION_SET_PROPERTY] = gem_create_set_pxp_type,
+	[DRM_XE_GEM_CREATE_SET_PROPERTY_PXP_TYPE] = gem_create_set_pxp_type,
 };
 
 static int gem_create_user_ext_set_property(struct xe_device *xe,

drivers/gpu/drm/xe/xe_device_sysfs.c

@@ -115,7 +115,7 @@ auto_link_downgrade_capable_show(struct device *dev, struct device_attribute *at
 	xe_pm_runtime_put(xe);
 
 	cap = REG_FIELD_GET(LINK_DOWNGRADE, val);
-	return sysfs_emit(buf, "%u\n", cap == DOWNGRADE_CAPABLE ? true : false);
+	return sysfs_emit(buf, "%u\n", cap == DOWNGRADE_CAPABLE);
 }
 static DEVICE_ATTR_ADMIN_RO(auto_link_downgrade_capable);
 

drivers/gpu/drm/xe/xe_device_types.h

@@ -325,6 +325,10 @@ struct xe_device {
 		u8 has_heci_gscfi:1;
 		/** @info.has_llc: Device has a shared CPU+GPU last level cache */
 		u8 has_llc:1;
+		/** @info.has_mbx_power_limits: Device has support to manage power limits using
+		 * pcode mailbox commands.
+		 */
+		u8 has_mbx_power_limits:1;
 		/** @info.has_pxp: Device has PXP support */
 		u8 has_pxp:1;
 		/** @info.has_range_tlb_invalidation: Has range based TLB invalidations */

drivers/gpu/drm/xe/xe_exec_queue.c

@@ -114,7 +114,6 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
 
 static int __xe_exec_queue_init(struct xe_exec_queue *q)
 {
-	struct xe_vm *vm = q->vm;
 	int i, err;
 	u32 flags = 0;
 
@@ -132,32 +131,20 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q)
 			flags |= XE_LRC_CREATE_RUNALONE;
 	}
 
-	if (vm) {
-		err = xe_vm_lock(vm, true);
-		if (err)
-			return err;
-	}
-
 	for (i = 0; i < q->width; ++i) {
 		q->lrc[i] = xe_lrc_create(q->hwe, q->vm, SZ_16K, q->msix_vec, flags);
 		if (IS_ERR(q->lrc[i])) {
 			err = PTR_ERR(q->lrc[i]);
-			goto err_unlock;
+			goto err_lrc;
 		}
 	}
 
-	if (vm)
-		xe_vm_unlock(vm);
-
 	err = q->ops->init(q);
 	if (err)
 		goto err_lrc;
 
 	return 0;
 
-err_unlock:
-	if (vm)
-		xe_vm_unlock(vm);
 err_lrc:
 	for (i = i - 1; i >= 0; --i)
 		xe_lrc_put(q->lrc[i]);

drivers/gpu/drm/xe/xe_gpu_scheduler.h

@@ -51,7 +51,15 @@ static inline void xe_sched_tdr_queue_imm(struct xe_gpu_scheduler *sched)
 
 static inline void xe_sched_resubmit_jobs(struct xe_gpu_scheduler *sched)
 {
-	drm_sched_resubmit_jobs(&sched->base);
+	struct drm_sched_job *s_job;
+
+	list_for_each_entry(s_job, &sched->base.pending_list, list) {
+		struct drm_sched_fence *s_fence = s_job->s_fence;
+		struct dma_fence *hw_fence = s_fence->parent;
+
+		if (hw_fence && !dma_fence_is_signaled(hw_fence))
+			sched->base.ops->run_job(s_job);
+	}
 }
 
 static inline bool

drivers/gpu/drm/xe/xe_guc_submit.c

@@ -229,6 +229,17 @@ static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q)
 static void guc_submit_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc *guc = arg;
+	struct xe_device *xe = guc_to_xe(guc);
+	struct xe_gt *gt = guc_to_gt(guc);
+	int ret;
+
+	ret = wait_event_timeout(guc->submission_state.fini_wq,
+				 xa_empty(&guc->submission_state.exec_queue_lookup),
+				 HZ * 5);
+
+	drain_workqueue(xe->destroy_wq);
+
+	xe_gt_assert(gt, ret);
 
 	xa_destroy(&guc->submission_state.exec_queue_lookup);
 }