[PATCH 16/55] drivers: hv: dxgkrnl: Query the dxgdevice state

[Eric Curtin <ericcurtin17@gmail.com>]

From: Iouri Tarassov <iourit@linux.microsoft.com>

Implement the ioctl to query the dxgdevice state - LX_DXGETDEVICESTATE.
The IOCTL is used to query the state of the given dxgdevice object (active,
error, etc.).

A call to the dxgdevice execution state could be high frequency.
The following method is used to avoid sending a synchronous VM
bus message to the host for every call:
- When a dxgdevice is created, a pointer to dxgglobal->device_state_counter
  is sent to the host
- Every time the device state on the host is changed, the host will send
  an asynchronous message to the guest (DXGK_VMBCOMMAND_SETGUESTDATA) and
  the guest will increment the device_state_counter value.
- the dxgdevice object has execution_state_counter member, which is equal
  to dxgglobal->device_state_counter value at the time when
  LX_DXGETDEVICESTATE was last processed..
- if execution_state_counter is different from device_state_counter, the
  dxgk_vmbcommand_getdevicestate VM bus message is sent to the host.
  Otherwise, the cached value is returned to the caller.

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>
---
 drivers/hv/dxgkrnl/dxgkrnl.h   |  11 ++++
 drivers/hv/dxgkrnl/dxgmodule.c |   1 -
 drivers/hv/dxgkrnl/dxgvmbus.c  |  68 ++++++++++++++++++++++
 drivers/hv/dxgkrnl/dxgvmbus.h  |  26 +++++++++
 drivers/hv/dxgkrnl/ioctl.c     |  66 ++++++++++++++++++++-
 include/uapi/misc/d3dkmthk.h   | 101 +++++++++++++++++++++++++++++----
 6 files changed, 261 insertions(+), 12 deletions(-)

diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h
index a39d11d76e41..b131c3b43838 100644
--- a/drivers/hv/dxgkrnl/dxgkrnl.h
+++ b/drivers/hv/dxgkrnl/dxgkrnl.h
@@ -268,12 +268,18 @@ void dxgsyncobject_destroy(struct dxgprocess *process,
 void dxgsyncobject_stop(struct dxgsyncobject *syncobj);
 void dxgsyncobject_release(struct kref *refcount);
 
+/*
+ * device_state_counter - incremented every time the execition state of
+ *	a DXGDEVICE is changed in the host. Used to optimize access to the
+ *	device execution state.
+ */
 struct dxgglobal {
 	struct dxgdriver	*drvdata;
 	struct dxgvmbuschannel	channel;
 	struct hv_device	*hdev;
 	u32			num_adapters;
 	u32			vmbus_ver;	/* Interface version */
+	atomic_t		device_state_counter;
 	struct resource		*mem;
 	u64			mmiospace_base;
 	u64			mmiospace_size;
@@ -512,6 +518,7 @@ struct dxgdevice {
 	struct list_head	syncobj_list_head;
 	struct d3dkmthandle	handle;
 	enum d3dkmt_deviceexecution_state execution_state;
+	int			execution_state_counter;
 	u32			handle_valid;
 };
 
@@ -849,6 +856,10 @@ int dxgvmb_send_open_sync_object_nt(struct dxgprocess *process,
 				    struct d3dkmt_opensyncobjectfromnthandle2
 				    *args,
 				    struct dxgsyncobject *syncobj);
+int dxgvmb_send_get_device_state(struct dxgprocess *process,
+				 struct dxgadapter *adapter,
+				 struct d3dkmt_getdevicestate *args,
+				 struct d3dkmt_getdevicestate *__user inargs);
 int dxgvmb_send_create_nt_shared_object(struct dxgprocess *process,
 					struct d3dkmthandle object,
 					struct d3dkmthandle *shared_handle);
diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c
index 8cbe1095599f..5c364a46b65f 100644
--- a/drivers/hv/dxgkrnl/dxgmodule.c
+++ b/drivers/hv/dxgkrnl/dxgmodule.c
@@ -827,7 +827,6 @@ static struct dxgglobal *dxgglobal_create(void)
 #ifdef DEBUG
 	dxgk_validate_ioctls();
 #endif
-
 	return dxgglobal;
 }
 
diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c
index 67a16de622e0..ed800dc09180 100644
--- a/drivers/hv/dxgkrnl/dxgvmbus.c
+++ b/drivers/hv/dxgkrnl/dxgvmbus.c
@@ -281,6 +281,24 @@ static void command_vm_to_host_init1(struct dxgkvmb_command_vm_to_host *command,
 	command->channel_type = DXGKVMB_VM_TO_HOST;
 }
 
+static void set_guest_data(struct dxgkvmb_command_host_to_vm *packet,
+			   u32 packet_length)
+{
+	struct dxgkvmb_command_setguestdata *command = (void *)packet;
+	struct dxgglobal *dxgglobal = dxggbl();
+
+	DXG_TRACE("Setting guest data: %d %d %p %p",
+		command->data_type,
+		command->data32,
+		command->guest_pointer,
+		&dxgglobal->device_state_counter);
+	if (command->data_type == SETGUESTDATA_DATATYPE_DWORD &&
+	    command->guest_pointer == &dxgglobal->device_state_counter &&
+	    command->data32 != 0) {
+		atomic_inc(&dxgglobal->device_state_counter);
+	}
+}
+
 static void signal_guest_event(struct dxgkvmb_command_host_to_vm *packet,
 			       u32 packet_length)
 {
@@ -311,6 +329,9 @@ static void process_inband_packet(struct dxgvmbuschannel *channel,
 			DXG_TRACE("global packet %d",
 				packet->command_type);
 			switch (packet->command_type) {
+			case DXGK_VMBCOMMAND_SETGUESTDATA:
+				set_guest_data(packet, packet_length);
+				break;
 			case DXGK_VMBCOMMAND_SIGNALGUESTEVENT:
 			case DXGK_VMBCOMMAND_SIGNALGUESTEVENTPASSIVE:
 				signal_guest_event(packet, packet_length);
@@ -1028,6 +1049,7 @@ struct d3dkmthandle dxgvmb_send_create_device(struct dxgadapter *adapter,
 	struct dxgkvmb_command_createdevice *command;
 	struct dxgkvmb_command_createdevice_return result = { };
 	struct dxgvmbusmsg msg;
+	struct dxgglobal *dxgglobal = dxggbl();
 
 	ret = init_message(&msg, adapter, process, sizeof(*command));
 	if (ret)
@@ -1037,6 +1059,7 @@ struct d3dkmthandle dxgvmb_send_create_device(struct dxgadapter *adapter,
 	command_vgpu_to_host_init2(&command->hdr, DXGK_VMBCOMMAND_CREATEDEVICE,
 				   process->host_handle);
 	command->flags = args->flags;
+	command->error_code = &dxgglobal->device_state_counter;
 
 	ret = dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size,
 				   &result, sizeof(result));
@@ -1806,6 +1829,51 @@ int dxgvmb_send_destroy_allocation(struct dxgprocess *process,
 	return ret;
 }
 
+int dxgvmb_send_get_device_state(struct dxgprocess *process,
+				 struct dxgadapter *adapter,
+				 struct d3dkmt_getdevicestate *args,
+				 struct d3dkmt_getdevicestate *__user output)
+{
+	int ret;
+	struct dxgkvmb_command_getdevicestate *command;
+	struct dxgkvmb_command_getdevicestate_return result = { };
+	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_GETDEVICESTATE,
+				   process->host_handle);
+	command->args = *args;
+
+	ret = dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size,
+				   &result, sizeof(result));
+	if (ret < 0)
+		goto cleanup;
+
+	ret = ntstatus2int(result.status);
+	if (ret < 0)
+		goto cleanup;
+
+	ret = copy_to_user(output, &result.args, sizeof(result.args));
+	if (ret) {
+		DXG_ERR("failed to copy output args");
+		ret = -EINVAL;
+	}
+
+	if (args->state_type == _D3DKMT_DEVICESTATE_EXECUTION)
+		args->execution_state = result.args.execution_state;
+
+cleanup:
+	free_message(&msg, process);
+	if (ret)
+		DXG_TRACE("err: %d", ret);
+	return ret;
+}
+
 int dxgvmb_send_open_resource(struct dxgprocess *process,
 			      struct dxgadapter *adapter,
 			      struct d3dkmthandle device,
diff --git a/drivers/hv/dxgkrnl/dxgvmbus.h b/drivers/hv/dxgkrnl/dxgvmbus.h
index c1f693917d99..6ca1068b0d4c 100644
--- a/drivers/hv/dxgkrnl/dxgvmbus.h
+++ b/drivers/hv/dxgkrnl/dxgvmbus.h
@@ -172,6 +172,22 @@ struct dxgkvmb_command_signalguestevent {
 	bool				dereference_event;
 };
 
+enum set_guestdata_type {
+	SETGUESTDATA_DATATYPE_DWORD	= 0,
+	SETGUESTDATA_DATATYPE_UINT64	= 1
+};
+
+struct dxgkvmb_command_setguestdata {
+	struct dxgkvmb_command_host_to_vm hdr;
+	void *guest_pointer;
+	union {
+		u64	data64;
+		u32	data32;
+	};
+	u32	dereference	: 1;
+	u32	data_type	: 4;
+};
+
 struct dxgkvmb_command_opensyncobject {
 	struct dxgkvmb_command_vm_to_host hdr;
 	struct d3dkmthandle		device;
@@ -574,6 +590,16 @@ struct dxgkvmb_command_destroyhwqueue {
 	struct d3dkmthandle		hwqueue;
 };
 
+struct dxgkvmb_command_getdevicestate {
+	struct dxgkvmb_command_vgpu_to_host hdr;
+	struct d3dkmt_getdevicestate	args;
+};
+
+struct dxgkvmb_command_getdevicestate_return {
+	struct d3dkmt_getdevicestate	args;
+	struct ntstatus			status;
+};
+
 struct dxgkvmb_command_shareobjectwithhost {
 	struct dxgkvmb_command_vm_to_host hdr;
 	struct d3dkmthandle	device_handle;
diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c
index ac052836ce27..26d410fd6e99 100644
--- a/drivers/hv/dxgkrnl/ioctl.c
+++ b/drivers/hv/dxgkrnl/ioctl.c
@@ -3142,6 +3142,70 @@ dxgkio_wait_sync_object_gpu(struct dxgprocess *process, void *__user inargs)
 	return ret;
 }
 
+static int
+dxgkio_get_device_state(struct dxgprocess *process, void *__user inargs)
+{
+	int ret;
+	struct d3dkmt_getdevicestate args;
+	struct dxgdevice *device = NULL;
+	struct dxgadapter *adapter = NULL;
+	int global_device_state_counter = 0;
+	struct dxgglobal *dxgglobal = dxggbl();
+
+	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;
+	}
+
+	if (args.state_type == _D3DKMT_DEVICESTATE_EXECUTION) {
+		global_device_state_counter =
+			atomic_read(&dxgglobal->device_state_counter);
+		if (device->execution_state_counter ==
+		    global_device_state_counter) {
+			args.execution_state = device->execution_state;
+			ret = copy_to_user(inargs, &args, sizeof(args));
+			if (ret) {
+				DXG_ERR("failed to copy args to user");
+				ret = -EINVAL;
+			}
+			goto cleanup;
+		}
+	}
+
+	ret = dxgvmb_send_get_device_state(process, adapter, &args, inargs);
+
+	if (ret == 0 && args.state_type == _D3DKMT_DEVICESTATE_EXECUTION) {
+		device->execution_state = args.execution_state;
+		device->execution_state_counter = global_device_state_counter;
+	}
+
+cleanup:
+
+	if (adapter)
+		dxgadapter_release_lock_shared(adapter);
+	if (device)
+		kref_put(&device->device_kref, dxgdevice_release);
+	if (ret < 0)
+		DXG_ERR("Failed to get device state %x", ret);
+
+	return ret;
+}
+
 static int
 dxgsharedsyncobj_get_host_nt_handle(struct dxgsharedsyncobject *syncobj,
 				    struct dxgprocess *process,
@@ -3822,7 +3886,7 @@ static struct ioctl_desc ioctls[] = {
 /* 0x0b */	{},
 /* 0x0c */	{},
 /* 0x0d */	{},
-/* 0x0e */	{},
+/* 0x0e */	{dxgkio_get_device_state, LX_DXGETDEVICESTATE},
 /* 0x0f */	{dxgkio_submit_command, LX_DXSUBMITCOMMAND},
 /* 0x10 */	{dxgkio_create_sync_object, LX_DXCREATESYNCHRONIZATIONOBJECT},
 /* 0x11 */	{dxgkio_signal_sync_object, LX_DXSIGNALSYNCHRONIZATIONOBJECT},
diff --git a/include/uapi/misc/d3dkmthk.h b/include/uapi/misc/d3dkmthk.h
index 895861505e6e..8a013b07e88a 100644
--- a/include/uapi/misc/d3dkmthk.h
+++ b/include/uapi/misc/d3dkmthk.h
@@ -236,6 +236,95 @@ struct d3dddi_destroypagingqueue {
 	struct d3dkmthandle		paging_queue;
 };
 
+enum dxgk_render_pipeline_stage {
+	_DXGK_RENDER_PIPELINE_STAGE_UNKNOWN		= 0,
+	_DXGK_RENDER_PIPELINE_STAGE_INPUT_ASSEMBLER	= 1,
+	_DXGK_RENDER_PIPELINE_STAGE_VERTEX_SHADER	= 2,
+	_DXGK_RENDER_PIPELINE_STAGE_GEOMETRY_SHADER	= 3,
+	_DXGK_RENDER_PIPELINE_STAGE_STREAM_OUTPUT	= 4,
+	_DXGK_RENDER_PIPELINE_STAGE_RASTERIZER		= 5,
+	_DXGK_RENDER_PIPELINE_STAGE_PIXEL_SHADER	= 6,
+	_DXGK_RENDER_PIPELINE_STAGE_OUTPUT_MERGER	= 7,
+};
+
+enum dxgk_page_fault_flags {
+	_DXGK_PAGE_FAULT_WRITE			= 0x1,
+	_DXGK_PAGE_FAULT_FENCE_INVALID		= 0x2,
+	_DXGK_PAGE_FAULT_ADAPTER_RESET_REQUIRED	= 0x4,
+	_DXGK_PAGE_FAULT_ENGINE_RESET_REQUIRED	= 0x8,
+	_DXGK_PAGE_FAULT_FATAL_HARDWARE_ERROR	= 0x10,
+	_DXGK_PAGE_FAULT_IOMMU			= 0x20,
+	_DXGK_PAGE_FAULT_HW_CONTEXT_VALID	= 0x40,
+	_DXGK_PAGE_FAULT_PROCESS_HANDLE_VALID	= 0x80,
+};
+
+enum dxgk_general_error_code {
+	_DXGK_GENERAL_ERROR_PAGE_FAULT		= 0,
+	_DXGK_GENERAL_ERROR_INVALID_INSTRUCTION	= 1,
+};
+
+struct dxgk_fault_error_code {
+	union {
+		struct {
+			__u32	is_device_specific_code:1;
+			enum dxgk_general_error_code general_error_code:31;
+		};
+		struct {
+			__u32	is_device_specific_code_reserved_bit:1;
+			__u32	device_specific_code:31;
+		};
+	};
+};
+
+struct d3dkmt_devicereset_state {
+	union {
+		struct {
+			__u32	desktop_switched:1;
+			__u32	reserved:31;
+		};
+		__u32		value;
+	};
+};
+
+struct d3dkmt_devicepagefault_state {
+	__u64				faulted_primitive_api_sequence_number;
+	enum dxgk_render_pipeline_stage	faulted_pipeline_stage;
+	__u32				faulted_bind_table_entry;
+	enum dxgk_page_fault_flags	page_fault_flags;
+	struct dxgk_fault_error_code	fault_error_code;
+	__u64				faulted_virtual_address;
+};
+
+enum d3dkmt_deviceexecution_state {
+	_D3DKMT_DEVICEEXECUTION_ACTIVE			= 1,
+	_D3DKMT_DEVICEEXECUTION_RESET			= 2,
+	_D3DKMT_DEVICEEXECUTION_HUNG			= 3,
+	_D3DKMT_DEVICEEXECUTION_STOPPED			= 4,
+	_D3DKMT_DEVICEEXECUTION_ERROR_OUTOFMEMORY	= 5,
+	_D3DKMT_DEVICEEXECUTION_ERROR_DMAFAULT		= 6,
+	_D3DKMT_DEVICEEXECUTION_ERROR_DMAPAGEFAULT	= 7,
+};
+
+enum d3dkmt_devicestate_type {
+	_D3DKMT_DEVICESTATE_EXECUTION		= 1,
+	_D3DKMT_DEVICESTATE_PRESENT		= 2,
+	_D3DKMT_DEVICESTATE_RESET		= 3,
+	_D3DKMT_DEVICESTATE_PRESENT_DWM		= 4,
+	_D3DKMT_DEVICESTATE_PAGE_FAULT		= 5,
+	_D3DKMT_DEVICESTATE_PRESENT_QUEUE	= 6,
+};
+
+struct d3dkmt_getdevicestate {
+	struct d3dkmthandle				device;
+	enum d3dkmt_devicestate_type			state_type;
+	union {
+		enum d3dkmt_deviceexecution_state	execution_state;
+		struct d3dkmt_devicereset_state		reset_state;
+		struct d3dkmt_devicepagefault_state	page_fault_state;
+		char alignment[48];
+	};
+};
+
 enum d3dkmdt_gdisurfacetype {
 	_D3DKMDT_GDISURFACE_INVALID				= 0,
 	_D3DKMDT_GDISURFACE_TEXTURE				= 1,
@@ -759,16 +848,6 @@ struct d3dkmt_queryadapterinfo {
 	__u32				private_data_size;
 };
 
-enum d3dkmt_deviceexecution_state {
-	_D3DKMT_DEVICEEXECUTION_ACTIVE			= 1,
-	_D3DKMT_DEVICEEXECUTION_RESET			= 2,
-	_D3DKMT_DEVICEEXECUTION_HUNG			= 3,
-	_D3DKMT_DEVICEEXECUTION_STOPPED			= 4,
-	_D3DKMT_DEVICEEXECUTION_ERROR_OUTOFMEMORY	= 5,
-	_D3DKMT_DEVICEEXECUTION_ERROR_DMAFAULT		= 6,
-	_D3DKMT_DEVICEEXECUTION_ERROR_DMAPAGEFAULT	= 7,
-};
-
 struct d3dddi_openallocationinfo2 {
 	struct d3dkmthandle	allocation;
 #ifdef __KERNEL__
@@ -978,6 +1057,8 @@ struct d3dkmt_shareobjectwithhost {
 	_IOWR(0x47, 0x07, struct d3dkmt_createpagingqueue)
 #define LX_DXQUERYADAPTERINFO		\
 	_IOWR(0x47, 0x09, struct d3dkmt_queryadapterinfo)
+#define LX_DXGETDEVICESTATE		\
+	_IOWR(0x47, 0x0e, struct d3dkmt_getdevicestate)
 #define LX_DXSUBMITCOMMAND		\
 	_IOWR(0x47, 0x0f, struct d3dkmt_submitcommand)
 #define LX_DXCREATESYNCHRONIZATIONOBJECT \