drivers: hv: dxgkrnl: Ioctl to put device to error state

Implement the ioctl to put the virtual compute device to the error
state (LX_DXMARKDEVICEASERROR).

This ioctl is used by the user mode driver when it detects an
unrecoverable error condition.

When a compute device is put to the error state, all subsequent
ioctl calls to the device will fail.

Signed-off-by: Iouri Tarassov <iourit@linux.microsoft.com>
[kms: forward port to 6.6 from 6.1. No code changes made.]
Signed-off-by: Kelsey Steele <kelseysteele@microsoft.com>

Author: Iouri Tarassov

drivers/hv/dxgkrnl/dxgkrnl.h

@@ -856,6 +856,9 @@ int dxgvmb_send_update_alloc_property(struct dxgprocess *process,
 				      struct d3dddi_updateallocproperty *args,
 				      struct d3dddi_updateallocproperty *__user
 				      inargs);
+int dxgvmb_send_mark_device_as_error(struct dxgprocess *process,
+				     struct dxgadapter *adapter,
+				     struct d3dkmt_markdeviceaserror *args);
 int dxgvmb_send_set_allocation_priority(struct dxgprocess *process,
 					struct dxgadapter *adapter,
 					struct d3dkmt_setallocationpriority *a);

drivers/hv/dxgkrnl/dxgvmbus.c

@@ -2730,6 +2730,31 @@ int dxgvmb_send_update_alloc_property(struct dxgprocess *process,
 	return ret;
 }
 
+int dxgvmb_send_mark_device_as_error(struct dxgprocess *process,
+				     struct dxgadapter *adapter,
+				     struct d3dkmt_markdeviceaserror *args)
+{
+	struct dxgkvmb_command_markdeviceaserror *command;
+	int ret;
+	struct dxgvmbusmsg msg = {.hdr = NULL};
+
+	ret = init_message(&msg, adapter, process, sizeof(*command));
+	if (ret)
+		goto cleanup;
+	command = (void *)msg.msg;
+
+	command_vgpu_to_host_init2(&command->hdr,
+				   DXGK_VMBCOMMAND_MARKDEVICEASERROR,
+				   process->host_handle);
+	command->args = *args;
+	ret = dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size);
+cleanup:
+	free_message(&msg, process);
+	if (ret)
+		DXG_TRACE("err: %d", ret);
+	return ret;
+}
+
 int dxgvmb_send_set_allocation_priority(struct dxgprocess *process,
 				struct dxgadapter *adapter,
 				struct d3dkmt_setallocationpriority *args)

drivers/hv/dxgkrnl/dxgvmbus.h

@@ -627,6 +627,11 @@ struct dxgkvmb_command_updateallocationproperty_return {
 	struct ntstatus			status;
 };
 
+struct dxgkvmb_command_markdeviceaserror {
+	struct dxgkvmb_command_vgpu_to_host hdr;
+	struct d3dkmt_markdeviceaserror args;
+};
+
 /* Returns ntstatus */
 struct dxgkvmb_command_changevideomemoryreservation {
 	struct dxgkvmb_command_vgpu_to_host hdr;

drivers/hv/dxgkrnl/ioctl.c

@@ -3341,6 +3341,42 @@ dxgkio_update_alloc_property(struct dxgprocess *process, void *__user inargs)
 	return ret;
 }
 
+static int
+dxgkio_mark_device_as_error(struct dxgprocess *process, void *__user inargs)
+{
+	struct d3dkmt_markdeviceaserror args;
+	struct dxgadapter *adapter = NULL;
+	struct dxgdevice *device = NULL;
+	int ret;
+
+	ret = copy_from_user(&args, inargs, sizeof(args));
+	if (ret) {
+		DXG_ERR("failed to copy input args");
+		ret = -EINVAL;
+		goto cleanup;
+	}
+	device = dxgprocess_device_by_handle(process, args.device);
+	if (device == NULL) {
+		ret = -EINVAL;
+		goto cleanup;
+	}
+	adapter = device->adapter;
+	ret = dxgadapter_acquire_lock_shared(adapter);
+	if (ret < 0) {
+		adapter = NULL;
+		goto cleanup;
+	}
+	device->execution_state = _D3DKMT_DEVICEEXECUTION_RESET;
+	ret = dxgvmb_send_mark_device_as_error(process, adapter, &args);
+cleanup:
+	if (adapter)
+		dxgadapter_release_lock_shared(adapter);
+	if (device)
+		kref_put(&device->device_kref, dxgdevice_release);
+	DXG_TRACE("ioctl:%s %d", errorstr(ret), ret);
+	return ret;
+}
+
 static int
 dxgkio_query_alloc_residency(struct dxgprocess *process, void *__user inargs)
 {
@@ -4404,7 +4440,7 @@ static struct ioctl_desc ioctls[] = {
 /* 0x23 */	{},
 /* 0x24 */	{},
 /* 0x25 */	{dxgkio_lock2, LX_DXLOCK2},
-/* 0x26 */	{},
+/* 0x26 */	{dxgkio_mark_device_as_error, LX_DXMARKDEVICEASERROR},
 /* 0x27 */	{},
 /* 0x28 */	{},
 /* 0x29 */	{},

include/uapi/misc/d3dkmthk.h

@@ -790,6 +790,16 @@ struct d3dkmt_unlock2 {
 	struct d3dkmthandle			allocation;
 };
 
+enum d3dkmt_device_error_reason {
+	_D3DKMT_DEVICE_ERROR_REASON_GENERIC		= 0x80000000,
+	_D3DKMT_DEVICE_ERROR_REASON_DRIVER_ERROR	= 0x80000006,
+};
+
+struct d3dkmt_markdeviceaserror {
+	struct d3dkmthandle			device;
+	enum d3dkmt_device_error_reason		reason;
+};
+
 enum d3dkmt_standardallocationtype {
 	_D3DKMT_STANDARDALLOCATIONTYPE_EXISTINGHEAP	= 1,
 	_D3DKMT_STANDARDALLOCATIONTYPE_CROSSADAPTER	= 2,
@@ -1290,6 +1300,8 @@ struct d3dkmt_shareobjectwithhost {
 	_IOWR(0x47, 0x1f, struct d3dkmt_flushheaptransitions)
 #define LX_DXLOCK2			\
 	_IOWR(0x47, 0x25, struct d3dkmt_lock2)
+#define LX_DXMARKDEVICEASERROR		\
+	_IOWR(0x47, 0x26, struct d3dkmt_markdeviceaserror)
 #define LX_DXQUERYALLOCATIONRESIDENCY	\
 	_IOWR(0x47, 0x2a, struct d3dkmt_queryallocationresidency)
 #define LX_DXSETALLOCATIONPRIORITY	\