Merge drm/drm-next into drm-intel-next

Sync to v6.10-rc3.

Signed-off-by: Jani Nikula <jani.nikula@intel.com>

8 files changed, 117 insertions, 53 deletions

diff --git a/drivers/gpu/drm/panthor/panthor_device.c b/drivers/gpu/drm/panthor/panthor_device.c
index 75276cbeba20..4082c8f2951d 100644
--- a/drivers/gpu/drm/panthor/panthor_device.c
+++ b/drivers/gpu/drm/panthor/panthor_device.c
@@ -129,13 +129,8 @@ static void panthor_device_reset_work(struct work_struct *work)
 	panthor_gpu_l2_power_on(ptdev);
 	panthor_mmu_post_reset(ptdev);
 	ret = panthor_fw_post_reset(ptdev);
-	if (ret)
-		goto out_dev_exit;
-
 	atomic_set(&ptdev->reset.pending, 0);
-	panthor_sched_post_reset(ptdev);
-
-out_dev_exit:
+	panthor_sched_post_reset(ptdev, ret != 0);
 	drm_dev_exit(cookie);
 
 	if (ret) {
@@ -293,6 +288,7 @@ static const struct panthor_exception_info panthor_exception_infos[] = {
 	PANTHOR_EXCEPTION(ACTIVE),
 	PANTHOR_EXCEPTION(CS_RES_TERM),
 	PANTHOR_EXCEPTION(CS_CONFIG_FAULT),
+	PANTHOR_EXCEPTION(CS_UNRECOVERABLE),
 	PANTHOR_EXCEPTION(CS_ENDPOINT_FAULT),
 	PANTHOR_EXCEPTION(CS_BUS_FAULT),
 	PANTHOR_EXCEPTION(CS_INSTR_INVALID),
diff --git a/drivers/gpu/drm/panthor/panthor_device.h b/drivers/gpu/drm/panthor/panthor_device.h
index 2fdd671b38fd..e388c0472ba7 100644
--- a/drivers/gpu/drm/panthor/panthor_device.h
+++ b/drivers/gpu/drm/panthor/panthor_device.h
@@ -216,6 +216,7 @@ enum drm_panthor_exception_type {
 	DRM_PANTHOR_EXCEPTION_CS_RES_TERM = 0x0f,
 	DRM_PANTHOR_EXCEPTION_MAX_NON_FAULT = 0x3f,
 	DRM_PANTHOR_EXCEPTION_CS_CONFIG_FAULT = 0x40,
+	DRM_PANTHOR_EXCEPTION_CS_UNRECOVERABLE = 0x41,
 	DRM_PANTHOR_EXCEPTION_CS_ENDPOINT_FAULT = 0x44,
 	DRM_PANTHOR_EXCEPTION_CS_BUS_FAULT = 0x48,
 	DRM_PANTHOR_EXCEPTION_CS_INSTR_INVALID = 0x49,
diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c
index 181395e2859a..857f3f11258a 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.c
+++ b/drivers/gpu/drm/panthor/panthor_fw.c
@@ -453,7 +453,7 @@ panthor_fw_alloc_queue_iface_mem(struct panthor_device *ptdev,
 
 	ret = panthor_kernel_bo_vmap(mem);
 	if (ret) {
-		panthor_kernel_bo_destroy(panthor_fw_vm(ptdev), mem);
+		panthor_kernel_bo_destroy(mem);
 		return ERR_PTR(ret);
 	}
 
@@ -1083,10 +1083,11 @@ int panthor_fw_post_reset(struct panthor_device *ptdev)
 		if (!ret)
 			goto out;
 
-		/* Force a disable, so we get a fresh boot on the next
-		 * panthor_fw_start() call.
+		/* Forcibly reset the MCU and force a slow reset, so we get a
+		 * fresh boot on the next panthor_fw_start() call.
 		 */
-		gpu_write(ptdev, MCU_CONTROL, MCU_CONTROL_DISABLE);
+		panthor_fw_stop(ptdev);
+		ptdev->fw->fast_reset = false;
 		drm_err(&ptdev->base, "FW fast reset failed, trying a slow reset");
 	}
 
@@ -1133,7 +1134,7 @@ void panthor_fw_unplug(struct panthor_device *ptdev)
 	panthor_fw_stop(ptdev);
 
 	list_for_each_entry(section, &ptdev->fw->sections, node)
-		panthor_kernel_bo_destroy(panthor_fw_vm(ptdev), section->mem);
+		panthor_kernel_bo_destroy(section->mem);
 
 	/* We intentionally don't call panthor_vm_idle() and let
 	 * panthor_mmu_unplug() release the AS we acquired with
@@ -1141,6 +1142,7 @@ void panthor_fw_unplug(struct panthor_device *ptdev)
 	 * state to keep the active_refcnt balanced.
 	 */
 	panthor_vm_put(ptdev->fw->vm);
+	ptdev->fw->vm = NULL;
 
 	panthor_gpu_power_off(ptdev, L2, ptdev->gpu_info.l2_present, 20000);
 }
diff --git a/drivers/gpu/drm/panthor/panthor_gem.c b/drivers/gpu/drm/panthor/panthor_gem.c
index d6483266d0c2..38f560864879 100644
--- a/drivers/gpu/drm/panthor/panthor_gem.c
+++ b/drivers/gpu/drm/panthor/panthor_gem.c
@@ -26,18 +26,18 @@ static void panthor_gem_free_object(struct drm_gem_object *obj)
 
 /**
  * panthor_kernel_bo_destroy() - Destroy a kernel buffer object
- * @vm: The VM this BO was mapped to.
  * @bo: Kernel buffer object to destroy. If NULL or an ERR_PTR(), the destruction
  * is skipped.
  */
-void panthor_kernel_bo_destroy(struct panthor_vm *vm,
-			       struct panthor_kernel_bo *bo)
+void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo)
 {
+	struct panthor_vm *vm;
 	int ret;
 
 	if (IS_ERR_OR_NULL(bo))
 		return;
 
+	vm = bo->vm;
 	panthor_kernel_bo_vunmap(bo);
 
 	if (drm_WARN_ON(bo->obj->dev,
@@ -53,6 +53,7 @@ void panthor_kernel_bo_destroy(struct panthor_vm *vm,
 	drm_gem_object_put(bo->obj);
 
 out_free_bo:
+	panthor_vm_put(vm);
 	kfree(bo);
 }
 
@@ -106,6 +107,7 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm,
 	if (ret)
 		goto err_free_va;
 
+	kbo->vm = panthor_vm_get(vm);
 	bo->exclusive_vm_root_gem = panthor_vm_root_gem(vm);
 	drm_gem_object_get(bo->exclusive_vm_root_gem);
 	bo->base.base.resv = bo->exclusive_vm_root_gem->resv;
diff --git a/drivers/gpu/drm/panthor/panthor_gem.h b/drivers/gpu/drm/panthor/panthor_gem.h
index 3bccba394d00..e43021cf6d45 100644
--- a/drivers/gpu/drm/panthor/panthor_gem.h
+++ b/drivers/gpu/drm/panthor/panthor_gem.h
@@ -62,6 +62,11 @@ struct panthor_kernel_bo {
 	struct drm_gem_object *obj;
 
 	/**
+	 * @vm: VM this private buffer is attached to.
+	 */
+	struct panthor_vm *vm;
+
+	/**
 	 * @va_node: VA space allocated to this GEM.
 	 */
 	struct drm_mm_node va_node;
@@ -136,7 +141,6 @@ panthor_kernel_bo_create(struct panthor_device *ptdev, struct panthor_vm *vm,
 			 size_t size, u32 bo_flags, u32 vm_map_flags,
 			 u64 gpu_va);
 
-void panthor_kernel_bo_destroy(struct panthor_vm *vm,
-			       struct panthor_kernel_bo *bo);
+void panthor_kernel_bo_destroy(struct panthor_kernel_bo *bo);
 
 #endif /* __PANTHOR_GEM_H__ */
diff --git a/drivers/gpu/drm/panthor/panthor_heap.c b/drivers/gpu/drm/panthor/panthor_heap.c
index 143fa35f2e74..3796a9eb22af 100644
--- a/drivers/gpu/drm/panthor/panthor_heap.c
+++ b/drivers/gpu/drm/panthor/panthor_heap.c
@@ -127,7 +127,7 @@ static void panthor_free_heap_chunk(struct panthor_vm *vm,
 	heap->chunk_count--;
 	mutex_unlock(&heap->lock);
 
-	panthor_kernel_bo_destroy(vm, chunk->bo);
+	panthor_kernel_bo_destroy(chunk->bo);
 	kfree(chunk);
 }
 
@@ -183,7 +183,7 @@ static int panthor_alloc_heap_chunk(struct panthor_device *ptdev,
 	return 0;
 
 err_destroy_bo:
-	panthor_kernel_bo_destroy(vm, chunk->bo);
+	panthor_kernel_bo_destroy(chunk->bo);
 
 err_free_chunk:
 	kfree(chunk);
@@ -253,8 +253,8 @@ int panthor_heap_destroy(struct panthor_heap_pool *pool, u32 handle)
  * @pool: Pool to instantiate the heap context from.
  * @initial_chunk_count: Number of chunk allocated at initialization time.
  * Must be at least 1.
- * @chunk_size: The size of each chunk. Must be a power of two between 256k
- * and 2M.
+ * @chunk_size: The size of each chunk. Must be page-aligned and lie in the
+ * [128k:8M] range.
  * @max_chunks: Maximum number of chunks that can be allocated.
  * @target_in_flight: Maximum number of in-flight render passes.
  * @heap_ctx_gpu_va: Pointer holding the GPU address of the allocated heap
@@ -281,8 +281,11 @@ int panthor_heap_create(struct panthor_heap_pool *pool,
 	if (initial_chunk_count == 0)
 		return -EINVAL;
 
-	if (hweight32(chunk_size) != 1 ||
-	    chunk_size < SZ_256K || chunk_size > SZ_2M)
+	if (initial_chunk_count > max_chunks)
+		return -EINVAL;
+
+	if (!IS_ALIGNED(chunk_size, PAGE_SIZE) ||
+	    chunk_size < SZ_128K || chunk_size > SZ_8M)
 		return -EINVAL;
 
 	down_read(&pool->lock);
@@ -320,7 +323,8 @@ int panthor_heap_create(struct panthor_heap_pool *pool,
 	if (!pool->vm) {
 		ret = -EINVAL;
 	} else {
-		ret = xa_alloc(&pool->xa, &id, heap, XA_LIMIT(1, MAX_HEAPS_PER_POOL), GFP_KERNEL);
+		ret = xa_alloc(&pool->xa, &id, heap,
+			       XA_LIMIT(0, MAX_HEAPS_PER_POOL - 1), GFP_KERNEL);
 		if (!ret) {
 			void *gpu_ctx = panthor_get_heap_ctx(pool, id);
 
@@ -391,7 +395,7 @@ int panthor_heap_return_chunk(struct panthor_heap_pool *pool,
 	mutex_unlock(&heap->lock);
 
 	if (removed) {
-		panthor_kernel_bo_destroy(pool->vm, chunk->bo);
+		panthor_kernel_bo_destroy(chunk->bo);
 		kfree(chunk);
 		ret = 0;
 	} else {
@@ -410,6 +414,13 @@ out_unlock:
  * @renderpasses_in_flight: Number of render passes currently in-flight.
  * @pending_frag_count: Number of fragment jobs waiting for execution/completion.
  * @new_chunk_gpu_va: Pointer used to return the chunk VA.
+ *
+ * Return:
+ * - 0 if a new heap was allocated
+ * - -ENOMEM if the tiler context reached the maximum number of chunks
+ *   or if too many render passes are in-flight
+ *   or if the allocation failed
+ * - -EINVAL if any of the arguments passed to panthor_heap_grow() is invalid
  */
 int panthor_heap_grow(struct panthor_heap_pool *pool,
 		      u64 heap_gpu_va,
@@ -439,10 +450,7 @@ int panthor_heap_grow(struct panthor_heap_pool *pool,
 	 * handler provided by the userspace driver, if any).
 	 */
 	if (renderpasses_in_flight > heap->target_in_flight ||
-	    (pending_frag_count > 0 && heap->chunk_count >= heap->max_chunks)) {
-		ret = -EBUSY;
-		goto out_unlock;
-	} else if (heap->chunk_count >= heap->max_chunks) {
+	    heap->chunk_count >= heap->max_chunks) {
 		ret = -ENOMEM;
 		goto out_unlock;
 	}
@@ -536,7 +544,7 @@ panthor_heap_pool_create(struct panthor_device *ptdev, struct panthor_vm *vm)
 	pool->vm = vm;
 	pool->ptdev = ptdev;
 	init_rwsem(&pool->lock);
-	xa_init_flags(&pool->xa, XA_FLAGS_ALLOC1);
+	xa_init_flags(&pool->xa, XA_FLAGS_ALLOC);
 	kref_init(&pool->refcount);
 
 	pool->gpu_contexts = panthor_kernel_bo_create(ptdev, vm, bosize,
@@ -587,7 +595,7 @@ void panthor_heap_pool_destroy(struct panthor_heap_pool *pool)
 		drm_WARN_ON(&pool->ptdev->base, panthor_heap_destroy_locked(pool, i));
 
 	if (!IS_ERR_OR_NULL(pool->gpu_contexts))
-		panthor_kernel_bo_destroy(pool->vm, pool->gpu_contexts);
+		panthor_kernel_bo_destroy(pool->gpu_contexts);
 
 	/* Reflects the fact the pool has been destroyed. */
 	pool->vm = NULL;
diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
index b3a51a6de523..79ffcbc41d78 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.c
+++ b/drivers/gpu/drm/panthor/panthor_sched.c
@@ -490,6 +490,18 @@ enum panthor_group_state {
 	 * Can no longer be scheduled. The only allowed action is a destruction.
 	 */
 	PANTHOR_CS_GROUP_TERMINATED,
+
+	/**
+	 * @PANTHOR_CS_GROUP_UNKNOWN_STATE: Group is an unknown state.
+	 *
+	 * The FW returned an inconsistent state. The group is flagged unusable
+	 * and can no longer be scheduled. The only allowed action is a
+	 * destruction.
+	 *
+	 * When that happens, we also schedule a FW reset, to start from a fresh
+	 * state.
+	 */
+	PANTHOR_CS_GROUP_UNKNOWN_STATE,
 };
 
 /**
@@ -814,8 +826,8 @@ static void group_free_queue(struct panthor_group *group, struct panthor_queue *
 
 	panthor_queue_put_syncwait_obj(queue);
 
-	panthor_kernel_bo_destroy(group->vm, queue->ringbuf);
-	panthor_kernel_bo_destroy(panthor_fw_vm(group->ptdev), queue->iface.mem);
+	panthor_kernel_bo_destroy(queue->ringbuf);
+	panthor_kernel_bo_destroy(queue->iface.mem);
 
 	kfree(queue);
 }
@@ -825,15 +837,14 @@ static void group_release_work(struct work_struct *work)
 	struct panthor_group *group = container_of(work,
 						   struct panthor_group,
 						   release_work);
-	struct panthor_device *ptdev = group->ptdev;
 	u32 i;
 
 	for (i = 0; i < group->queue_count; i++)
 		group_free_queue(group, group->queues[i]);
 
-	panthor_kernel_bo_destroy(panthor_fw_vm(ptdev), group->suspend_buf);
-	panthor_kernel_bo_destroy(panthor_fw_vm(ptdev), group->protm_suspend_buf);
-	panthor_kernel_bo_destroy(group->vm, group->syncobjs);
+	panthor_kernel_bo_destroy(group->suspend_buf);
+	panthor_kernel_bo_destroy(group->protm_suspend_buf);
+	panthor_kernel_bo_destroy(group->syncobjs);
 
 	panthor_vm_put(group->vm);
 	kfree(group);
@@ -1127,6 +1138,7 @@ csg_slot_sync_state_locked(struct panthor_device *ptdev, u32 csg_id)
 	struct panthor_fw_csg_iface *csg_iface;
 	struct panthor_group *group;
 	enum panthor_group_state new_state, old_state;
+	u32 csg_state;
 
 	lockdep_assert_held(&ptdev->scheduler->lock);
 
@@ -1137,7 +1149,8 @@ csg_slot_sync_state_locked(struct panthor_device *ptdev, u32 csg_id)
 		return;
 
 	old_state = group->state;
-	switch (csg_iface->output->ack & CSG_STATE_MASK) {
+	csg_state = csg_iface->output->ack & CSG_STATE_MASK;
+	switch (csg_state) {
 	case CSG_STATE_START:
 	case CSG_STATE_RESUME:
 		new_state = PANTHOR_CS_GROUP_ACTIVE;
@@ -1148,11 +1161,28 @@ csg_slot_sync_state_locked(struct panthor_device *ptdev, u32 csg_id)
 	case CSG_STATE_SUSPEND:
 		new_state = PANTHOR_CS_GROUP_SUSPENDED;
 		break;
+	default:
+		/* The unknown state might be caused by a FW state corruption,
+		 * which means the group metadata can't be trusted anymore, and
+		 * the SUSPEND operation might propagate the corruption to the
+		 * suspend buffers. Flag the group state as unknown to make
+		 * sure it's unusable after that point.
+		 */
+		drm_err(&ptdev->base, "Invalid state on CSG %d (state=%d)",
+			csg_id, csg_state);
+		new_state = PANTHOR_CS_GROUP_UNKNOWN_STATE;
+		break;
 	}
 
 	if (old_state == new_state)
 		return;
 
+	/* The unknown state might be caused by a FW issue, reset the FW to
+	 * take a fresh start.
+	 */
+	if (new_state == PANTHOR_CS_GROUP_UNKNOWN_STATE)
+		panthor_device_schedule_reset(ptdev);
+
 	if (new_state == PANTHOR_CS_GROUP_SUSPENDED)
 		csg_slot_sync_queues_state_locked(ptdev, csg_id);
 
@@ -1250,7 +1280,16 @@ cs_slot_process_fatal_event_locked(struct panthor_device *ptdev,
 	if (group)
 		group->fatal_queues |= BIT(cs_id);
 
-	sched_queue_delayed_work(sched, tick, 0);
+	if (CS_EXCEPTION_TYPE(fatal) == DRM_PANTHOR_EXCEPTION_CS_UNRECOVERABLE) {
+		/* If this exception is unrecoverable, queue a reset, and make
+		 * sure we stop scheduling groups until the reset has happened.
+		 */
+		panthor_device_schedule_reset(ptdev);
+		cancel_delayed_work(&sched->tick_work);
+	} else {
+		sched_queue_delayed_work(sched, tick, 0);
+	}
+
 	drm_warn(&ptdev->base,
 		 "CSG slot %d CS slot: %d\n"
 		 "CS_FATAL.EXCEPTION_TYPE: 0x%x (%s)\n"
@@ -1354,7 +1393,12 @@ static int group_process_tiler_oom(struct panthor_group *group, u32 cs_id)
 					pending_frag_count, &new_chunk_va);
 	}
 
-	if (ret && ret != -EBUSY) {
+	/* If the heap context doesn't have memory for us, we want to let the
+	 * FW try to reclaim memory by waiting for fragment jobs to land or by
+	 * executing the tiler OOM exception handler, which is supposed to
+	 * implement incremental rendering.
+	 */
+	if (ret && ret != -ENOMEM) {
 		drm_warn(&ptdev->base, "Failed to extend the tiler heap\n");
 		group->fatal_queues |= BIT(cs_id);
 		sched_queue_delayed_work(sched, tick, 0);
@@ -1783,6 +1827,7 @@ static bool
 group_can_run(struct panthor_group *group)
 {
 	return group->state != PANTHOR_CS_GROUP_TERMINATED &&
+	       group->state != PANTHOR_CS_GROUP_UNKNOWN_STATE &&
 	       !group->destroyed && group->fatal_queues == 0 &&
 	       !group->timedout;
 }
@@ -2546,8 +2591,8 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 {
 	struct panthor_scheduler *sched = ptdev->scheduler;
 	struct panthor_csg_slots_upd_ctx upd_ctx;
-	u32 suspended_slots, faulty_slots;
 	struct panthor_group *group;
+	u32 suspended_slots;
 	u32 i;
 
 	mutex_lock(&sched->lock);
@@ -2557,7 +2602,8 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 
 		if (csg_slot->group) {
 			csgs_upd_ctx_queue_reqs(ptdev, &upd_ctx, i,
-						CSG_STATE_SUSPEND,
+						group_can_run(csg_slot->group) ?
+						CSG_STATE_SUSPEND : CSG_STATE_TERMINATE,
 						CSG_STATE_MASK);
 		}
 	}
@@ -2566,10 +2612,9 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 
 	csgs_upd_ctx_apply_locked(ptdev, &upd_ctx);
 	suspended_slots &= ~upd_ctx.timedout_mask;
-	faulty_slots = upd_ctx.timedout_mask;
 
-	if (faulty_slots) {
-		u32 slot_mask = faulty_slots;
+	if (upd_ctx.timedout_mask) {
+		u32 slot_mask = upd_ctx.timedout_mask;
 
 		drm_err(&ptdev->base, "CSG suspend failed, escalating to termination");
 		csgs_upd_ctx_init(&upd_ctx);
@@ -2620,9 +2665,6 @@ void panthor_sched_suspend(struct panthor_device *ptdev)
 
 			slot_mask &= ~BIT(csg_id);
 		}
-
-		if (flush_caches_failed)
-			faulty_slots |= suspended_slots;
 	}
 
 	for (i = 0; i < sched->csg_slot_count; i++) {
@@ -2691,15 +2733,22 @@ void panthor_sched_pre_reset(struct panthor_device *ptdev)
 	mutex_unlock(&sched->reset.lock);
 }
 
-void panthor_sched_post_reset(struct panthor_device *ptdev)
+void panthor_sched_post_reset(struct panthor_device *ptdev, bool reset_failed)
 {
 	struct panthor_scheduler *sched = ptdev->scheduler;
 	struct panthor_group *group, *group_tmp;
 
 	mutex_lock(&sched->reset.lock);
 
-	list_for_each_entry_safe(group, group_tmp, &sched->reset.stopped_groups, run_node)
+	list_for_each_entry_safe(group, group_tmp, &sched->reset.stopped_groups, run_node) {
+		/* Consider all previously running group as terminated if the
+		 * reset failed.
+		 */
+		if (reset_failed)
+			group->state = PANTHOR_CS_GROUP_TERMINATED;
+
 		panthor_group_start(group);
+	}
 
 	/* We're done resetting the GPU, clear the reset.in_progress bit so we can
 	 * kick the scheduler.
@@ -2707,9 +2756,11 @@ void panthor_sched_post_reset(struct panthor_device *ptdev)
 	atomic_set(&sched->reset.in_progress, false);
 	mutex_unlock(&sched->reset.lock);
 
-	sched_queue_delayed_work(sched, tick, 0);
-
-	sched_queue_work(sched, sync_upd);
+	/* No need to queue a tick and update syncs if the reset failed. */
+	if (!reset_failed) {
+		sched_queue_delayed_work(sched, tick, 0);
+		sched_queue_work(sched, sync_upd);
+	}
 }
 
 static void group_sync_upd_work(struct work_struct *work)
diff --git a/drivers/gpu/drm/panthor/panthor_sched.h b/drivers/gpu/drm/panthor/panthor_sched.h
index 66438b1f331f..3a30d2328b30 100644
--- a/drivers/gpu/drm/panthor/panthor_sched.h
+++ b/drivers/gpu/drm/panthor/panthor_sched.h
@@ -40,7 +40,7 @@ void panthor_group_pool_destroy(struct panthor_file *pfile);
 int panthor_sched_init(struct panthor_device *ptdev);
 void panthor_sched_unplug(struct panthor_device *ptdev);
 void panthor_sched_pre_reset(struct panthor_device *ptdev);
-void panthor_sched_post_reset(struct panthor_device *ptdev);
+void panthor_sched_post_reset(struct panthor_device *ptdev, bool reset_failed);
 void panthor_sched_suspend(struct panthor_device *ptdev);
 void panthor_sched_resume(struct panthor_device *ptdev);