Merge tag 'drm-xe-fixes-2025-02-27' of https://gitlab.freedesktop.org/drm/xe/kernel into drm-fixes

uAPI:
- OA uapi fix (Umesh)

Driver:
- Userptr related fixes (Auld)
- Remove a duplicated register entry (Mingong)
- Scheduler related fix to prevent exec races when freeing it (Tejas)

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

From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/Z8CSqJre1VCjPXt2@intel.com

4 files changed, 38 insertions, 10 deletions

diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index d86219dedde2..b732c89816df 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -53,7 +53,6 @@
 
 #define RING_CTL(base)				XE_REG((base) + 0x3c)
 #define   RING_CTL_SIZE(size)			((size) - PAGE_SIZE) /* in bytes -> pages */
-#define   RING_CTL_SIZE(size)			((size) - PAGE_SIZE) /* in bytes -> pages */
 
 #define RING_START_UDW(base)			XE_REG((base) + 0x48)
 
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 913c74d6e2ae..b6a2dd742ebd 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1248,6 +1248,8 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 
 	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);
 	release_guc_id(guc, q);
 	xe_sched_entity_fini(&ge->entity);
 	xe_sched_fini(&ge->sched);
diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index fa873f3d0a9d..eb6cd91e1e22 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -1689,7 +1689,7 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
 	stream->oa_buffer.format = &stream->oa->oa_formats[param->oa_format];
 
 	stream->sample = param->sample;
-	stream->periodic = param->period_exponent > 0;
+	stream->periodic = param->period_exponent >= 0;
 	stream->period_exponent = param->period_exponent;
 	stream->no_preempt = param->no_preempt;
 	stream->wait_num_reports = param->wait_num_reports;
@@ -1970,6 +1970,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 	}
 
 	param.xef = xef;
+	param.period_exponent = -1;
 	ret = xe_oa_user_extensions(oa, XE_OA_USER_EXTN_FROM_OPEN, data, 0, &param);
 	if (ret)
 		return ret;
@@ -2024,7 +2025,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		goto err_exec_q;
 	}
 
-	if (param.period_exponent > 0) {
+	if (param.period_exponent >= 0) {
 		u64 oa_period, oa_freq_hz;
 
 		/* Requesting samples from OAG buffer is a privileged operation */
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 690330352d4c..30259eba450b 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -666,20 +666,33 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 
 	/* Collect invalidated userptrs */
 	spin_lock(&vm->userptr.invalidated_lock);
+	xe_assert(vm->xe, list_empty(&vm->userptr.repin_list));
 	list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated,
 				 userptr.invalidate_link) {
 		list_del_init(&uvma->userptr.invalidate_link);
-		list_move_tail(&uvma->userptr.repin_link,
-			       &vm->userptr.repin_list);
+		list_add_tail(&uvma->userptr.repin_link,
+			      &vm->userptr.repin_list);
 	}
 	spin_unlock(&vm->userptr.invalidated_lock);
 
-	/* Pin and move to temporary list */
+	/* Pin and move to bind list */
 	list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
 				 userptr.repin_link) {
 		err = xe_vma_userptr_pin_pages(uvma);
 		if (err == -EFAULT) {
 			list_del_init(&uvma->userptr.repin_link);
+			/*
+			 * We might have already done the pin once already, but
+			 * then had to retry before the re-bind happened, due
+			 * some other condition in the caller, but in the
+			 * meantime the userptr got dinged by the notifier such
+			 * that we need to revalidate here, but this time we hit
+			 * the EFAULT. In such a case make sure we remove
+			 * ourselves from the rebind list to avoid going down in
+			 * flames.
+			 */
+			if (!list_empty(&uvma->vma.combined_links.rebind))
+				list_del_init(&uvma->vma.combined_links.rebind);
 
 			/* Wait for pending binds */
 			xe_vm_lock(vm, false);
@@ -690,10 +703,10 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 			err = xe_vm_invalidate_vma(&uvma->vma);
 			xe_vm_unlock(vm);
 			if (err)
-				return err;
+				break;
 		} else {
-			if (err < 0)
-				return err;
+			if (err)
+				break;
 
 			list_del_init(&uvma->userptr.repin_link);
 			list_move_tail(&uvma->vma.combined_links.rebind,
@@ -701,7 +714,19 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 		}
 	}
 
-	return 0;
+	if (err) {
+		down_write(&vm->userptr.notifier_lock);
+		spin_lock(&vm->userptr.invalidated_lock);
+		list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
+					 userptr.repin_link) {
+			list_del_init(&uvma->userptr.repin_link);
+			list_move_tail(&uvma->userptr.invalidate_link,
+				       &vm->userptr.invalidated);
+		}
+		spin_unlock(&vm->userptr.invalidated_lock);
+		up_write(&vm->userptr.notifier_lock);
+	}
+	return err;
 }
 
 /**
@@ -1066,6 +1091,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
 		xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED);
 
 		spin_lock(&vm->userptr.invalidated_lock);
+		xe_assert(vm->xe, list_empty(&to_userptr_vma(vma)->userptr.repin_link));
 		list_del(&to_userptr_vma(vma)->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	} else if (!xe_vma_is_null(vma)) {