Merge tag 'drm-misc-fixes-2024-10-10' of https://gitlab.freedesktop.org/drm/misc/kernel into drm-fixes

Short summary of fixes pull:

fbdev-dma:
- Only clean up deferred I/O if instanciated

nouveau:
- dmem: Fix privileged error in copy engine channel; Fix possible
data leak in migrate_to_ram()
- gsp: Fix coding style

sched:
- Avoid leaking lockdep map

v3d:
- Stop active perfmon before destroying it

vc4:
- Stop active perfmon before destroying it

xe:
- Drop GuC submit_wq pool

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

From: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20241010133708.GA461532@localhost.localdomain

9 files changed, 31 insertions, 88 deletions

diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c
index b0602c4f3628..51c2d742d199 100644
--- a/drivers/gpu/drm/drm_fbdev_dma.c
+++ b/drivers/gpu/drm/drm_fbdev_dma.c
@@ -50,7 +50,8 @@ static void drm_fbdev_dma_fb_destroy(struct fb_info *info)
 	if (!fb_helper->dev)
 		return;
 
-	fb_deferred_io_cleanup(info);
+	if (info->fbdefio)
+		fb_deferred_io_cleanup(info);
 	drm_fb_helper_fini(fb_helper);
 
 	drm_client_buffer_vunmap(fb_helper->buffer);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
index 9e6f39912368..a2055f2a014a 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/gsp.h
@@ -210,7 +210,7 @@ struct nvkm_gsp {
 	} *rm;
 
 	struct {
-		struct mutex mutex;;
+		struct mutex mutex;
 		struct idr idr;
 	} client_id;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c
index 1f2d649f4b96..1a072568cef6 100644
--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c
@@ -193,7 +193,7 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf)
 	if (!spage || !(src & MIGRATE_PFN_MIGRATE))
 		goto done;
 
-	dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address);
+	dpage = alloc_page_vma(GFP_HIGHUSER | __GFP_ZERO, vmf->vma, vmf->address);
 	if (!dpage)
 		goto done;
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index f6e78dba594f..34985771b2a2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -331,7 +331,7 @@ nouveau_accel_ce_init(struct nouveau_drm *drm)
 		return;
 	}
 
-	ret = nouveau_channel_new(&drm->client, false, runm, NvDmaFB, NvDmaTT, &drm->cechan);
+	ret = nouveau_channel_new(&drm->client, true, runm, NvDmaFB, NvDmaTT, &drm->cechan);
 	if (ret)
 		NV_ERROR(drm, "failed to create ce channel, %d\n", ret);
 }
diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
index 6f27cab0b76d..eaef20f41786 100644
--- a/drivers/gpu/drm/scheduler/sched_main.c
+++ b/drivers/gpu/drm/scheduler/sched_main.c
@@ -87,6 +87,12 @@
 #define CREATE_TRACE_POINTS
 #include "gpu_scheduler_trace.h"
 
+#ifdef CONFIG_LOCKDEP
+static struct lockdep_map drm_sched_lockdep_map = {
+	.name = "drm_sched_lockdep_map"
+};
+#endif
+
 #define to_drm_sched_job(sched_job)		\
 		container_of((sched_job), struct drm_sched_job, queue_node)
 
@@ -1269,7 +1275,12 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		sched->submit_wq = submit_wq;
 		sched->own_submit_wq = false;
 	} else {
+#ifdef CONFIG_LOCKDEP
+		sched->submit_wq = alloc_ordered_workqueue_lockdep_map(name, 0,
+								       &drm_sched_lockdep_map);
+#else
 		sched->submit_wq = alloc_ordered_workqueue(name, 0);
+#endif
 		if (!sched->submit_wq)
 			return -ENOMEM;
 
diff --git a/drivers/gpu/drm/v3d/v3d_perfmon.c b/drivers/gpu/drm/v3d/v3d_perfmon.c
index cd7f1eedf17f..00cd081d7873 100644
--- a/drivers/gpu/drm/v3d/v3d_perfmon.c
+++ b/drivers/gpu/drm/v3d/v3d_perfmon.c
@@ -306,6 +306,11 @@ void v3d_perfmon_open_file(struct v3d_file_priv *v3d_priv)
 static int v3d_perfmon_idr_del(int id, void *elem, void *data)
 {
 	struct v3d_perfmon *perfmon = elem;
+	struct v3d_dev *v3d = (struct v3d_dev *)data;
+
+	/* If the active perfmon is being destroyed, stop it first */
+	if (perfmon == v3d->active_perfmon)
+		v3d_perfmon_stop(v3d, perfmon, false);
 
 	v3d_perfmon_put(perfmon);
 
@@ -314,8 +319,10 @@ static int v3d_perfmon_idr_del(int id, void *elem, void *data)
 
 void v3d_perfmon_close_file(struct v3d_file_priv *v3d_priv)
 {
+	struct v3d_dev *v3d = v3d_priv->v3d;
+
 	mutex_lock(&v3d_priv->perfmon.lock);
-	idr_for_each(&v3d_priv->perfmon.idr, v3d_perfmon_idr_del, NULL);
+	idr_for_each(&v3d_priv->perfmon.idr, v3d_perfmon_idr_del, v3d);
 	idr_destroy(&v3d_priv->perfmon.idr);
 	mutex_unlock(&v3d_priv->perfmon.lock);
 	mutex_destroy(&v3d_priv->perfmon.lock);
diff --git a/drivers/gpu/drm/vc4/vc4_perfmon.c b/drivers/gpu/drm/vc4/vc4_perfmon.c
index c4ac2c946238..c00a5cc2316d 100644
--- a/drivers/gpu/drm/vc4/vc4_perfmon.c
+++ b/drivers/gpu/drm/vc4/vc4_perfmon.c
@@ -116,6 +116,11 @@ void vc4_perfmon_open_file(struct vc4_file *vc4file)
 static int vc4_perfmon_idr_del(int id, void *elem, void *data)
 {
 	struct vc4_perfmon *perfmon = elem;
+	struct vc4_dev *vc4 = (struct vc4_dev *)data;
+
+	/* If the active perfmon is being destroyed, stop it first */
+	if (perfmon == vc4->active_perfmon)
+		vc4_perfmon_stop(vc4, perfmon, false);
 
 	vc4_perfmon_put(perfmon);
 
@@ -130,7 +135,7 @@ void vc4_perfmon_close_file(struct vc4_file *vc4file)
 		return;
 
 	mutex_lock(&vc4file->perfmon.lock);
-	idr_for_each(&vc4file->perfmon.idr, vc4_perfmon_idr_del, NULL);
+	idr_for_each(&vc4file->perfmon.idr, vc4_perfmon_idr_del, vc4);
 	idr_destroy(&vc4file->perfmon.idr);
 	mutex_unlock(&vc4file->perfmon.lock);
 	mutex_destroy(&vc4file->perfmon.lock);
diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 80062e1d3f66..bf3836614aca 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -224,80 +224,11 @@ static bool exec_queue_killed_or_banned_or_wedged(struct xe_exec_queue *q)
 		 EXEC_QUEUE_STATE_BANNED));
 }
 
-#ifdef CONFIG_PROVE_LOCKING
-static int alloc_submit_wq(struct xe_guc *guc)
-{
-	int i;
-
-	for (i = 0; i < NUM_SUBMIT_WQ; ++i) {
-		guc->submission_state.submit_wq_pool[i] =
-			alloc_ordered_workqueue("submit_wq", 0);
-		if (!guc->submission_state.submit_wq_pool[i])
-			goto err_free;
-	}
-
-	return 0;
-
-err_free:
-	while (i)
-		destroy_workqueue(guc->submission_state.submit_wq_pool[--i]);
-
-	return -ENOMEM;
-}
-
-static void free_submit_wq(struct xe_guc *guc)
-{
-	int i;
-
-	for (i = 0; i < NUM_SUBMIT_WQ; ++i)
-		destroy_workqueue(guc->submission_state.submit_wq_pool[i]);
-}
-
-static struct workqueue_struct *get_submit_wq(struct xe_guc *guc)
-{
-	int idx = guc->submission_state.submit_wq_idx++ % NUM_SUBMIT_WQ;
-
-	return guc->submission_state.submit_wq_pool[idx];
-}
-#else
-static int alloc_submit_wq(struct xe_guc *guc)
-{
-	return 0;
-}
-
-static void free_submit_wq(struct xe_guc *guc)
-{
-
-}
-
-static struct workqueue_struct *get_submit_wq(struct xe_guc *guc)
-{
-	return NULL;
-}
-#endif
-
-static void xe_guc_submit_fini(struct xe_guc *guc)
-{
-	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);
-}
-
 static void guc_submit_fini(struct drm_device *drm, void *arg)
 {
 	struct xe_guc *guc = arg;
 
-	xe_guc_submit_fini(guc);
 	xa_destroy(&guc->submission_state.exec_queue_lookup);
-	free_submit_wq(guc);
 }
 
 static void guc_submit_wedged_fini(void *arg)
@@ -359,10 +290,6 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids)
 	if (err)
 		return err;
 
-	err = alloc_submit_wq(guc);
-	if (err)
-		return err;
-
 	gt->exec_queue_ops = &guc_exec_queue_ops;
 
 	xa_init(&guc->submission_state.exec_queue_lookup);
@@ -1482,8 +1409,7 @@ static int guc_exec_queue_init(struct xe_exec_queue *q)
 	timeout = (q->vm && xe_vm_in_lr_mode(q->vm)) ? MAX_SCHEDULE_TIMEOUT :
 		  msecs_to_jiffies(q->sched_props.job_timeout_ms);
 	err = xe_sched_init(&ge->sched, &drm_sched_ops, &xe_sched_ops,
-			    get_submit_wq(guc),
-			    q->lrc[0]->ring.size / MAX_JOB_SIZE_BYTES, 64,
+			    NULL, q->lrc[0]->ring.size / MAX_JOB_SIZE_BYTES, 64,
 			    timeout, guc_to_gt(guc)->ordered_wq, NULL,
 			    q->name, gt_to_xe(q->gt)->drm.dev);
 	if (err)
diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h
index 69046f698271..ed150fc09ad0 100644
--- a/drivers/gpu/drm/xe/xe_guc_types.h
+++ b/drivers/gpu/drm/xe/xe_guc_types.h
@@ -72,13 +72,6 @@ struct xe_guc {
 		atomic_t stopped;
 		/** @submission_state.lock: protects submission state */
 		struct mutex lock;
-#ifdef CONFIG_PROVE_LOCKING
-#define NUM_SUBMIT_WQ	256
-		/** @submission_state.submit_wq_pool: submission ordered workqueues pool */
-		struct workqueue_struct *submit_wq_pool[NUM_SUBMIT_WQ];
-		/** @submission_state.submit_wq_idx: submission ordered workqueue index */
-		int submit_wq_idx;
-#endif
 		/** @submission_state.enabled: submission is enabled */
 		bool enabled;
 		/** @submission_state.fini_wq: submit fini wait queue */