drm/msm: Add VM_BIND submitqueue

This submitqueue type isn't tied to a hw ringbuffer, but instead
executes on the CPU for performing async VM_BIND ops.

Signed-off-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
Tested-by: Antonino Maniscalco <antomani103@gmail.com>
Reviewed-by: Antonino Maniscalco <antomani103@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/661517/

Author: robclark

drivers/gpu/drm/msm/msm_gem.h

@@ -53,6 +53,13 @@ struct msm_gem_vm {
 	/** @base: Inherit from drm_gpuvm. */
 	struct drm_gpuvm base;
 
+	/**
+	 * @sched: Scheduler used for asynchronous VM_BIND request.
+	 *
+	 * Unused for kernel managed VMs (where all operations are synchronous).
+	 */
+	struct drm_gpu_scheduler sched;
+
 	/**
 	 * @mm: Memory management for kernel managed VA allocations
 	 *
@@ -71,6 +78,9 @@ struct msm_gem_vm {
 	 */
 	struct pid *pid;
 
+	/** @last_fence: Fence for last pending work scheduled on the VM */
+	struct dma_fence *last_fence;
+
 	/** @faults: the number of GPU hangs associated with this address space */
 	int faults;
 
@@ -100,6 +110,8 @@ struct drm_gpuvm *
 msm_gem_vm_create(struct drm_device *drm, struct msm_mmu *mmu, const char *name,
 		  u64 va_start, u64 va_size, bool managed);
 
+void msm_gem_vm_close(struct drm_gpuvm *gpuvm);
+
 struct msm_fence_context;
 
 #define MSM_VMA_DUMP (DRM_GPUVA_USERBITS << 0)

drivers/gpu/drm/msm/msm_gem_submit.c

@@ -4,6 +4,7 @@
  * Author: Rob Clark <robdclark@gmail.com>
  */
 
+#include <linux/dma-fence-unwrap.h>
 #include <linux/file.h>
 #include <linux/sync_file.h>
 #include <linux/uaccess.h>
@@ -259,29 +260,47 @@ static int submit_lookup_cmds(struct msm_gem_submit *submit,
 static int submit_lock_objects(struct msm_gem_submit *submit)
 {
 	unsigned flags = DRM_EXEC_INTERRUPTIBLE_WAIT;
+	struct drm_exec *exec = &submit->exec;
 	int ret;
 
+	if (msm_context_is_vmbind(submit->queue->ctx)) {
+		flags |= DRM_EXEC_IGNORE_DUPLICATES;
+
+		drm_exec_init(&submit->exec, flags, submit->nr_bos);
+
+		drm_exec_until_all_locked (&submit->exec) {
+			ret = drm_gpuvm_prepare_vm(submit->vm, exec, 1);
+			drm_exec_retry_on_contention(exec);
+			if (ret)
+				return ret;
+
+			ret = drm_gpuvm_prepare_objects(submit->vm, exec, 1);
+			drm_exec_retry_on_contention(exec);
+			if (ret)
+				return ret;
+		}
+
+		return 0;
+	}
+
 	drm_exec_init(&submit->exec, flags, submit->nr_bos);
 
 	drm_exec_until_all_locked (&submit->exec) {
 		ret = drm_exec_lock_obj(&submit->exec,
 					drm_gpuvm_resv_obj(submit->vm));
 		drm_exec_retry_on_contention(&submit->exec);
 		if (ret)
-			goto error;
+			return ret;
 		for (unsigned i = 0; i < submit->nr_bos; i++) {
 			struct drm_gem_object *obj = submit->bos[i].obj;
 			ret = drm_exec_prepare_obj(&submit->exec, obj, 1);
 			drm_exec_retry_on_contention(&submit->exec);
 			if (ret)
-				goto error;
+				return ret;
 		}
 	}
 
 	return 0;
-
-error:
-	return ret;
 }
 
 static int submit_fence_sync(struct msm_gem_submit *submit)
@@ -367,9 +386,18 @@ static void submit_unpin_objects(struct msm_gem_submit *submit)
 
 static void submit_attach_object_fences(struct msm_gem_submit *submit)
 {
-	int i;
+	struct msm_gem_vm *vm = to_msm_vm(submit->vm);
+	struct dma_fence *last_fence;
+
+	if (msm_context_is_vmbind(submit->queue->ctx)) {
+		drm_gpuvm_resv_add_fence(submit->vm, &submit->exec,
+					 submit->user_fence,
+					 DMA_RESV_USAGE_BOOKKEEP,
+					 DMA_RESV_USAGE_BOOKKEEP);
+		return;
+	}
 
-	for (i = 0; i < submit->nr_bos; i++) {
+	for (unsigned i = 0; i < submit->nr_bos; i++) {
 		struct drm_gem_object *obj = submit->bos[i].obj;
 
 		if (submit->bos[i].flags & MSM_SUBMIT_BO_WRITE)
@@ -379,6 +407,10 @@ static void submit_attach_object_fences(struct msm_gem_submit *submit)
 			dma_resv_add_fence(obj->resv, submit->user_fence,
 					   DMA_RESV_USAGE_READ);
 	}
+
+	last_fence = vm->last_fence;
+	vm->last_fence = dma_fence_unwrap_merge(submit->user_fence, last_fence);
+	dma_fence_put(last_fence);
 }
 
 static int submit_bo(struct msm_gem_submit *submit, uint32_t idx,
@@ -537,6 +569,11 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 	if (!queue)
 		return -ENOENT;
 
+	if (queue->flags & MSM_SUBMITQUEUE_VM_BIND) {
+		ret = UERR(EINVAL, dev, "Invalid queue type");
+		goto out_post_unlock;
+	}
+
 	ring = gpu->rb[queue->ring_nr];
 
 	if (args->flags & MSM_SUBMIT_FENCE_FD_OUT) {
@@ -727,6 +764,18 @@ int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 
 	submit_attach_object_fences(submit);
 
+	if (msm_context_is_vmbind(ctx)) {
+		/*
+		 * If we are not using VM_BIND, submit_pin_vmas() will validate
+		 * just the BOs attached to the submit.  In that case we don't
+		 * need to validate the _entire_ vm, because userspace tracked
+		 * what BOs are associated with the submit.
+		 */
+		ret = drm_gpuvm_validate(submit->vm, &submit->exec);
+		if (ret)
+			goto out;
+	}
+
 	/* The scheduler owns a ref now: */
 	msm_gem_submit_get(submit);
 

drivers/gpu/drm/msm/msm_gem_vma.c

@@ -16,6 +16,7 @@ msm_gem_vm_free(struct drm_gpuvm *gpuvm)
 	drm_mm_takedown(&vm->mm);
 	if (vm->mmu)
 		vm->mmu->funcs->destroy(vm->mmu);
+	dma_fence_put(vm->last_fence);
 	put_pid(vm->pid);
 	kfree(vm);
 }
@@ -154,6 +155,9 @@ static const struct drm_gpuvm_ops msm_gpuvm_ops = {
 	.vm_free = msm_gem_vm_free,
 };
 
+static const struct drm_sched_backend_ops msm_vm_bind_ops = {
+};
+
 /**
  * msm_gem_vm_create() - Create and initialize a &msm_gem_vm
  * @drm: the drm device
@@ -195,6 +199,21 @@ msm_gem_vm_create(struct drm_device *drm, struct msm_mmu *mmu, const char *name,
 		goto err_free_vm;
 	}
 
+	if (!managed) {
+		struct drm_sched_init_args args = {
+			.ops = &msm_vm_bind_ops,
+			.num_rqs = 1,
+			.credit_limit = 1,
+			.timeout = MAX_SCHEDULE_TIMEOUT,
+			.name = "msm-vm-bind",
+			.dev = drm->dev,
+		};
+
+		ret = drm_sched_init(&vm->sched, &args);
+		if (ret)
+			goto err_free_dummy;
+	}
+
 	drm_gpuvm_init(&vm->base, name, flags, drm, dummy_gem,
 		       va_start, va_size, 0, 0, &msm_gpuvm_ops);
 	drm_gem_object_put(dummy_gem);
@@ -206,8 +225,60 @@ msm_gem_vm_create(struct drm_device *drm, struct msm_mmu *mmu, const char *name,
 
 	return &vm->base;
 
+err_free_dummy:
+	drm_gem_object_put(dummy_gem);
+
 err_free_vm:
 	kfree(vm);
 	return ERR_PTR(ret);
 
 }
+
+/**
+ * msm_gem_vm_close() - Close a VM
+ * @gpuvm: The VM to close
+ *
+ * Called when the drm device file is closed, to tear down VM related resources
+ * (which will drop refcounts to GEM objects that were still mapped into the
+ * VM at the time).
+ */
+void
+msm_gem_vm_close(struct drm_gpuvm *gpuvm)
+{
+	struct msm_gem_vm *vm = to_msm_vm(gpuvm);
+	struct drm_gpuva *vma, *tmp;
+
+	/*
+	 * For kernel managed VMs, the VMAs are torn down when the handle is
+	 * closed, so nothing more to do.
+	 */
+	if (vm->managed)
+		return;
+
+	if (vm->last_fence)
+		dma_fence_wait(vm->last_fence, false);
+
+	/* Kill the scheduler now, so we aren't racing with it for cleanup: */
+	drm_sched_stop(&vm->sched, NULL);
+	drm_sched_fini(&vm->sched);
+
+	/* Tear down any remaining mappings: */
+	dma_resv_lock(drm_gpuvm_resv(gpuvm), NULL);
+	drm_gpuvm_for_each_va_safe (vma, tmp, gpuvm) {
+		struct drm_gem_object *obj = vma->gem.obj;
+
+		if (obj && obj->resv != drm_gpuvm_resv(gpuvm)) {
+			drm_gem_object_get(obj);
+			msm_gem_lock(obj);
+		}
+
+		msm_gem_vma_unmap(vma);
+		msm_gem_vma_close(vma);
+
+		if (obj && obj->resv != drm_gpuvm_resv(gpuvm)) {
+			msm_gem_unlock(obj);
+			drm_gem_object_put(obj);
+		}
+	}
+	dma_resv_unlock(drm_gpuvm_resv(gpuvm));
+}

drivers/gpu/drm/msm/msm_gpu.h

@@ -564,6 +564,9 @@ struct msm_gpu_submitqueue {
 	struct mutex lock;
 	struct kref ref;
 	struct drm_sched_entity *entity;
+
+	/** @_vm_bind_entity: used for @entity pointer for VM_BIND queues */
+	struct drm_sched_entity _vm_bind_entity[0];
 };
 
 struct msm_gpu_state_bo {

drivers/gpu/drm/msm/msm_submitqueue.c

@@ -72,6 +72,9 @@ void msm_submitqueue_destroy(struct kref *kref)
 
 	idr_destroy(&queue->fence_idr);
 
+	if (queue->entity == &queue->_vm_bind_entity[0])
+		drm_sched_entity_destroy(queue->entity);
+
 	msm_context_put(queue->ctx);
 
 	kfree(queue);
@@ -102,7 +105,7 @@ struct msm_gpu_submitqueue *msm_submitqueue_get(struct msm_context *ctx,
 
 void msm_submitqueue_close(struct msm_context *ctx)
 {
-	struct msm_gpu_submitqueue *entry, *tmp;
+	struct msm_gpu_submitqueue *queue, *tmp;
 
 	if (!ctx)
 		return;
@@ -111,10 +114,17 @@ void msm_submitqueue_close(struct msm_context *ctx)
 	 * No lock needed in close and there won't
 	 * be any more user ioctls coming our way
 	 */
-	list_for_each_entry_safe(entry, tmp, &ctx->submitqueues, node) {
-		list_del(&entry->node);
-		msm_submitqueue_put(entry);
+	list_for_each_entry_safe(queue, tmp, &ctx->submitqueues, node) {
+		if (queue->entity == &queue->_vm_bind_entity[0])
+			drm_sched_entity_flush(queue->entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
+		list_del(&queue->node);
+		msm_submitqueue_put(queue);
 	}
+
+	if (!ctx->vm)
+		return;
+
+	msm_gem_vm_close(ctx->vm);
 }
 
 static struct drm_sched_entity *
@@ -160,8 +170,6 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_context *ctx,
 	struct msm_drm_private *priv = drm->dev_private;
 	struct msm_gpu_submitqueue *queue;
 	enum drm_sched_priority sched_prio;
-	extern int enable_preemption;
-	bool preemption_supported;
 	unsigned ring_nr;
 	int ret;
 
@@ -171,26 +179,53 @@ int msm_submitqueue_create(struct drm_device *drm, struct msm_context *ctx,
 	if (!priv->gpu)
 		return -ENODEV;
 
-	preemption_supported = priv->gpu->nr_rings == 1 && enable_preemption != 0;
+	if (flags & MSM_SUBMITQUEUE_VM_BIND) {
+		unsigned sz;
 
-	if (flags & MSM_SUBMITQUEUE_ALLOW_PREEMPT && preemption_supported)
-		return -EINVAL;
+		/* Not allowed for kernel managed VMs (ie. kernel allocs VA) */
+		if (!msm_context_is_vmbind(ctx))
+			return -EINVAL;
 
-	ret = msm_gpu_convert_priority(priv->gpu, prio, &ring_nr, &sched_prio);
-	if (ret)
-		return ret;
+		if (prio)
+			return -EINVAL;
+
+		sz = struct_size(queue, _vm_bind_entity, 1);
+		queue = kzalloc(sz, GFP_KERNEL);
+	} else {
+		extern int enable_preemption;
+		bool preemption_supported =
+			priv->gpu->nr_rings == 1 && enable_preemption != 0;
+
+		if (flags & MSM_SUBMITQUEUE_ALLOW_PREEMPT && preemption_supported)
+			return -EINVAL;
 
-	queue = kzalloc(sizeof(*queue), GFP_KERNEL);
+		ret = msm_gpu_convert_priority(priv->gpu, prio, &ring_nr, &sched_prio);
+		if (ret)
+			return ret;
+
+		queue = kzalloc(sizeof(*queue), GFP_KERNEL);
+	}
 
 	if (!queue)
 		return -ENOMEM;
 
 	kref_init(&queue->ref);
 	queue->flags = flags;
-	queue->ring_nr = ring_nr;
 
-	queue->entity = get_sched_entity(ctx, priv->gpu->rb[ring_nr],
-					 ring_nr, sched_prio);
+	if (flags & MSM_SUBMITQUEUE_VM_BIND) {
+		struct drm_gpu_scheduler *sched = &to_msm_vm(msm_context_vm(drm, ctx))->sched;
+
+		queue->entity = &queue->_vm_bind_entity[0];
+
+		drm_sched_entity_init(queue->entity, DRM_SCHED_PRIORITY_KERNEL,
+				      &sched, 1, NULL);
+	} else {
+		queue->ring_nr = ring_nr;
+
+		queue->entity = get_sched_entity(ctx, priv->gpu->rb[ring_nr],
+						 ring_nr, sched_prio);
+	}
+
 	if (IS_ERR(queue->entity)) {
 		ret = PTR_ERR(queue->entity);
 		kfree(queue);