drivers: hv: dxgkrnl: Implementation of submit command, paging and hardware queue.

Implement various IOCTLs to deal with hardware queues and  paging queues.
Hardware queues are used when a compute device supports "hardware
scheduling". This means that the compute device itself schedules execution
of DMA buffers from hardware queues without CPU intervention. This is as
oppose to the "packet scheduling" mode where the software GPU scheduler
on the host schedules DMA buffer execution.

LX_DXSUBMITCOMMAND
   This IOCTL is used to submit GPU commands when the device supports the
   "packet scheduling" mode.

LX_DXSUBMITCOMMANDTOHWQUEUE
   This IOCTL is used to submit GPU commands when the device supports the
   "hardware scheduling" mode.

LX_DXCREATEPAGINGQUEUE, LX_DXDESTROYPAGINGQUEUE
   These IOCTLs are used to create/destroy a paging queue.
   Paging queues are used to handle residency of device accessible
   allocations. An allocation is resident, when the device has access to
   it. For example, the allocation resides in local device memory or
   device page tables point to system memory which is made non-pageable.

LX_DXCREATEHWQUEUE, LX_DXDESTROYHWQUEUE
   These IOCTLs are used to create/destroy hardware queue objects.
   Hardware queues are used when the compute device supports the
   "hardware scheduling" mode.

Signed-off-by: Iouri Tarassov <iourit@linux.microsoft.com>

Author: Iouri Tarassov

drivers/hv/dxgkrnl/dxgadapter.c

@@ -729,6 +729,26 @@ void dxgdevice_release(struct kref *refcount)
 	vfree(device);
 }
 
+void dxgdevice_add_paging_queue(struct dxgdevice *device,
+				struct dxgpagingqueue *entry)
+{
+	dxgdevice_acquire_alloc_list_lock(device);
+	list_add_tail(&entry->pqueue_list_entry, &device->pqueue_list_head);
+	dxgdevice_release_alloc_list_lock(device);
+}
+
+void dxgdevice_remove_paging_queue(struct dxgpagingqueue *pqueue)
+{
+	struct dxgdevice *device = pqueue->device;
+
+	dxgdevice_acquire_alloc_list_lock(device);
+	if (pqueue->pqueue_list_entry.next) {
+		list_del(&pqueue->pqueue_list_entry);
+		pqueue->pqueue_list_entry.next = NULL;
+	}
+	dxgdevice_release_alloc_list_lock(device);
+}
+
 void dxgdevice_add_syncobj(struct dxgdevice *device,
 			   struct dxgsyncobject *syncobj)
 {
@@ -820,6 +840,38 @@ void dxgcontext_release(struct kref *refcount)
 	vfree(context);
 }
 
+int dxgcontext_add_hwqueue(struct dxgcontext *context,
+			   struct dxghwqueue *hwqueue)
+{
+	int ret = 0;
+
+	down_write(&context->hwqueue_list_lock);
+	if (dxgcontext_is_active(context))
+		list_add_tail(&hwqueue->hwqueue_list_entry,
+			      &context->hwqueue_list_head);
+	else
+		ret = -ENODEV;
+	up_write(&context->hwqueue_list_lock);
+	return ret;
+}
+
+void dxgcontext_remove_hwqueue(struct dxgcontext *context,
+			       struct dxghwqueue *hwqueue)
+{
+	if (hwqueue->hwqueue_list_entry.next) {
+		list_del(&hwqueue->hwqueue_list_entry);
+		hwqueue->hwqueue_list_entry.next = NULL;
+	}
+}
+
+void dxgcontext_remove_hwqueue_safe(struct dxgcontext *context,
+				    struct dxghwqueue *hwqueue)
+{
+	down_write(&context->hwqueue_list_lock);
+	dxgcontext_remove_hwqueue(context, hwqueue);
+	up_write(&context->hwqueue_list_lock);
+}
+
 struct dxgallocation *dxgallocation_create(struct dxgprocess *process)
 {
 	struct dxgallocation *alloc = vzalloc(sizeof(struct dxgallocation));
@@ -890,6 +942,59 @@ void dxgallocation_destroy(struct dxgallocation *alloc)
 	vfree(alloc);
 }
 
+struct dxgpagingqueue *dxgpagingqueue_create(struct dxgdevice *device)
+{
+	struct dxgpagingqueue *pqueue;
+
+	pqueue = vzalloc(sizeof(*pqueue));
+	if (pqueue) {
+		pqueue->device = device;
+		pqueue->process = device->process;
+		pqueue->device_handle = device->handle;
+		dxgdevice_add_paging_queue(device, pqueue);
+	}
+	return pqueue;
+}
+
+void dxgpagingqueue_stop(struct dxgpagingqueue *pqueue)
+{
+	int ret;
+
+	if (pqueue->mapped_address) {
+		ret = dxg_unmap_iospace(pqueue->mapped_address, PAGE_SIZE);
+		dev_dbg(dxgglobaldev, "fence is unmapped %d %p",
+			    ret, pqueue->mapped_address);
+		pqueue->mapped_address = NULL;
+	}
+}
+
+void dxgpagingqueue_destroy(struct dxgpagingqueue *pqueue)
+{
+	struct dxgprocess *process = pqueue->process;
+
+	dev_dbg(dxgglobaldev, "%s %p %x\n", __func__, pqueue, pqueue->handle.v);
+
+	dxgpagingqueue_stop(pqueue);
+
+	hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL);
+	if (pqueue->handle.v) {
+		hmgrtable_free_handle(&process->handle_table,
+				      HMGRENTRY_TYPE_DXGPAGINGQUEUE,
+				      pqueue->handle);
+		pqueue->handle.v = 0;
+	}
+	if (pqueue->syncobj_handle.v) {
+		hmgrtable_free_handle(&process->handle_table,
+				      HMGRENTRY_TYPE_MONITOREDFENCE,
+				      pqueue->syncobj_handle);
+		pqueue->syncobj_handle.v = 0;
+	}
+	hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL);
+	if (pqueue->device)
+		dxgdevice_remove_paging_queue(pqueue);
+	vfree(pqueue);
+}
+
 struct dxgprocess_adapter *dxgprocess_adapter_create(struct dxgprocess *process,
 						     struct dxgadapter *adapter)
 {
@@ -1188,8 +1293,8 @@ void dxgsyncobject_stop(struct dxgsyncobject *syncobj)
 						      PAGE_SIZE);
 
 				(void)ret;
-				dev_dbg(dxgglobaldev, "fence is unmapped %d %p\n",
-					    ret, syncobj->mapped_address);
+				dev_dbg(dxgglobaldev, "unmap fence %d %p\n",
+					ret, syncobj->mapped_address);
 				syncobj->mapped_address = NULL;
 			}
 		}
@@ -1212,18 +1317,59 @@ void dxgsyncobject_release(struct kref *refcount)
 	vfree(syncobj);
 }
 
-void dxghwqueue_destroy(struct dxgprocess *process, struct dxghwqueue *hwqueue)
+struct dxghwqueue *dxghwqueue_create(struct dxgcontext *context)
 {
-	/* Placeholder */
+	struct dxgprocess *process = context->device->process;
+	struct dxghwqueue *hwqueue = vzalloc(sizeof(*hwqueue));
+
+	if (hwqueue) {
+		kref_init(&hwqueue->hwqueue_kref);
+		hwqueue->context = context;
+		hwqueue->process = process;
+		hwqueue->device_handle = context->device->handle;
+		if (dxgcontext_add_hwqueue(context, hwqueue) < 0) {
+			kref_put(&hwqueue->hwqueue_kref, dxghwqueue_release);
+			hwqueue = NULL;
+		} else {
+			kref_get(&context->context_kref);
+		}
+	}
+	return hwqueue;
 }
 
-void dxgpagingqueue_destroy(struct dxgpagingqueue *pqueue)
+void dxghwqueue_destroy(struct dxgprocess *process, struct dxghwqueue *hwqueue)
 {
-	/* Placeholder */
+	dev_dbg(dxgglobaldev, "%s %p\n", __func__, hwqueue);
+	hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL);
+	if (hwqueue->handle.v) {
+		hmgrtable_free_handle(&process->handle_table,
+				      HMGRENTRY_TYPE_DXGHWQUEUE,
+				      hwqueue->handle);
+		hwqueue->handle.v = 0;
+	}
+	if (hwqueue->progress_fence_sync_object.v) {
+		hmgrtable_free_handle(&process->handle_table,
+				      HMGRENTRY_TYPE_MONITOREDFENCE,
+				      hwqueue->progress_fence_sync_object);
+		hwqueue->progress_fence_sync_object.v = 0;
+	}
+	hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL);
+
+	if (hwqueue->progress_fence_mapped_address) {
+		dxg_unmap_iospace(hwqueue->progress_fence_mapped_address,
+				  PAGE_SIZE);
+		hwqueue->progress_fence_mapped_address = NULL;
+	}
+	dxgcontext_remove_hwqueue_safe(hwqueue->context, hwqueue);
+
+	kref_put(&hwqueue->context->context_kref, dxgcontext_release);
+	kref_put(&hwqueue->hwqueue_kref, dxghwqueue_release);
 }
 
-void dxgpagingqueue_stop(struct dxgpagingqueue *pqueue)
+void dxghwqueue_release(struct kref *refcount)
 {
-	/* Placeholder */
-}
+	struct dxghwqueue *hwqueue;
 
+	hwqueue = container_of(refcount, struct dxghwqueue, hwqueue_kref);
+	vfree(hwqueue);
+}

drivers/hv/dxgkrnl/dxgkrnl.h

@@ -943,5 +943,7 @@ int dxgvmb_send_get_stdalloc_data(struct dxgdevice *device,
 int dxgvmb_send_query_statistics(struct dxgprocess *process,
 				 struct dxgadapter *adapter,
 				 struct d3dkmt_querystatistics *args);
+int dxgvmb_send_share_object_with_host(struct dxgprocess *process,
+				struct d3dkmt_shareobjectwithhost *args);
 
 #endif