Drivers: hv: Add modules to expose /dev/mshv to VMMs running on Hyper-V

Add mshv, mshv_root, and mshv_vtl modules.
- mshv provides /dev/mshv and common code, and is the parent module
- mshv_root provides APIs for creating and managing child partitions
- mshv_vtl provides VTL (Virtual Trust Level) support for VMMs

Signed-off-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>

drivers/hv/Kconfig

@@ -54,4 +54,58 @@ config HYPERV_BALLOON
 	help
 	  Select this option to enable Hyper-V Balloon driver.
 
+config MSHV
+	tristate "Microsoft Hypervisor root partition interfaces: /dev/mshv"
+	depends on X86_64 && HYPERV
+	select EVENTFD
+	select MSHV_VFIO
+	select MSHV_XFER_TO_GUEST_WORK
+	help
+	  Select this option to enable core functionality for managing guest
+	  virtual machines running under the Microsoft Hypervisor.
+
+	  The interfaces are provided via a device named /dev/mshv.
+
+	  To compile this as a module, choose M here.
+
+	  If unsure, say N.
+
+config MSHV_ROOT
+	tristate "Microsoft Hyper-V root partition APIs driver"
+	depends on MSHV
+	help
+	  Select this option to provide /dev/mshv interfaces specific to
+	  running as the root partition on Microsoft Hypervisor.
+
+	  To compile this as a module, choose M here.
+
+	  If unsure, say N.
+
+config MSHV_VTL
+	tristate "Microsoft Hyper-V VTL driver"
+	depends on MSHV
+	select HYPERV_VTL_MODE
+	select TRANSPARENT_HUGEPAGE
+	help
+	  Select this option to enable Hyper-V VTL driver.
+	  Virtual Secure Mode (VSM) is a set of hypervisor capabilities and
+	  enlightenments offered to host and guest partitions which enables
+	  the creation and management of new security boundaries within
+	  operating system software.
+
+	  VSM achieves and maintains isolation through Virtual Trust Levels
+	  (VTLs). Virtual Trust Levels are hierarchical, with higher levels
+	  being more privileged than lower levels. VTL0 is the least privileged
+	  level, and currently only other level supported is VTL2.
+
+	  To compile this as a module, choose M here.
+
+	  If unsure, say N.
+
+config MSHV_VFIO
+	bool
+
+config MSHV_XFER_TO_GUEST_WORK
+	bool
+
 endmenu

drivers/hv/Makefile

@@ -2,10 +2,31 @@
 obj-$(CONFIG_HYPERV)		+= hv_vmbus.o
 obj-$(CONFIG_HYPERV_UTILS)	+= hv_utils.o
 obj-$(CONFIG_HYPERV_BALLOON)	+= hv_balloon.o
+obj-$(CONFIG_DXGKRNL)		+= dxgkrnl/
+obj-$(CONFIG_MSHV)			+= mshv.o
+obj-$(CONFIG_MSHV_VTL)		+= mshv_vtl.o
+obj-$(CONFIG_MSHV_ROOT)		+= mshv_root.o
 
 CFLAGS_hv_trace.o = -I$(src)
 CFLAGS_hv_balloon.o = -I$(src)
 
+CFLAGS_mshv_main.o			= -DHV_HYPERV_DEFS
+CFLAGS_hv_call.o			= -DHV_HYPERV_DEFS
+CFLAGS_mshv_root_main.o		= -DHV_HYPERV_DEFS
+CFLAGS_mshv_root_hv_call.o	= -DHV_HYPERV_DEFS
+CFLAGS_mshv_synic.o			= -DHV_HYPERV_DEFS
+CFLAGS_mshv_portid_table.o	= -DHV_HYPERV_DEFS
+CFLAGS_mshv_eventfd.o		= -DHV_HYPERV_DEFS
+CFLAGS_mshv_msi.o			= -DHV_HYPERV_DEFS
+CFLAGS_mshv_vtl_main.o		= -DHV_HYPERV_DEFS
+
+mshv-y				+= mshv_main.o
+mshv_root-y			:= mshv_root_main.o mshv_synic.o mshv_portid_table.o \
+						mshv_eventfd.o mshv_msi.o mshv_root_hv_call.o hv_call.o
+mshv_vtl-y			:= mshv_vtl_main.o hv_call.o
+
+obj-$(CONFIG_MSHV_XFER_TO_GUEST_WORK) += xfer_to_guest.o
+
 hv_vmbus-y := vmbus_drv.o \
 		 hv.o connection.o channel.o \
 		 channel_mgmt.o ring_buffer.o hv_trace.o

drivers/hv/hv_call.c

@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2023, Microsoft Corporation.
+ *
+ * Hypercall helper functions shared between mshv modules.
+ *
+ * Authors:
+ *   Nuno Das Neves <nunodasneves@linux.microsoft.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <asm/mshyperv.h>
+
+#define HV_GET_REGISTER_BATCH_SIZE	\
+	(HV_HYP_PAGE_SIZE / sizeof(union hv_register_value))
+#define HV_SET_REGISTER_BATCH_SIZE	\
+	((HV_HYP_PAGE_SIZE - sizeof(struct hv_input_set_vp_registers)) \
+		/ sizeof(struct hv_register_assoc))
+
+int hv_call_get_vp_registers(
+		u32 vp_index,
+		u64 partition_id,
+		u16 count,
+		union hv_input_vtl input_vtl,
+		struct hv_register_assoc *registers)
+{
+	struct hv_input_get_vp_registers *input_page;
+	union hv_register_value *output_page;
+	u16 completed = 0;
+	unsigned long remaining = count;
+	int rep_count, i;
+	u64 status;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	output_page = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+	input_page->partition_id = partition_id;
+	input_page->vp_index = vp_index;
+	input_page->input_vtl.as_uint8 = input_vtl.as_uint8;
+	input_page->rsvd_z8 = 0;
+	input_page->rsvd_z16 = 0;
+
+	while (remaining) {
+		rep_count = min(remaining, HV_GET_REGISTER_BATCH_SIZE);
+		for (i = 0; i < rep_count; ++i)
+			input_page->names[i] = registers[i].name;
+
+		status = hv_do_rep_hypercall(HVCALL_GET_VP_REGISTERS, rep_count,
+					     0, input_page, output_page);
+		if (!hv_result_success(status)) {
+			pr_err("%s: completed %li out of %u, %s\n",
+			       __func__,
+			       count - remaining, count,
+			       hv_status_to_string(status));
+			break;
+		}
+		completed = hv_repcomp(status);
+		for (i = 0; i < completed; ++i)
+			registers[i].value = output_page[i];
+
+		registers += completed;
+		remaining -= completed;
+	}
+	local_irq_restore(flags);
+
+	return hv_status_to_errno(status);
+}
+
+int hv_call_set_vp_registers(
+		u32 vp_index,
+		u64 partition_id,
+		u16 count,
+		union hv_input_vtl input_vtl,
+		struct hv_register_assoc *registers)
+{
+	struct hv_input_set_vp_registers *input_page;
+	u16 completed = 0;
+	unsigned long remaining = count;
+	int rep_count;
+	u64 status;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	input_page->partition_id = partition_id;
+	input_page->vp_index = vp_index;
+	input_page->input_vtl.as_uint8 = input_vtl.as_uint8;
+	input_page->rsvd_z8 = 0;
+	input_page->rsvd_z16 = 0;
+
+	while (remaining) {
+		rep_count = min(remaining, HV_SET_REGISTER_BATCH_SIZE);
+		memcpy(input_page->elements, registers,
+			sizeof(struct hv_register_assoc) * rep_count);
+
+		status = hv_do_rep_hypercall(HVCALL_SET_VP_REGISTERS, rep_count,
+					     0, input_page, NULL);
+		if (!hv_result_success(status)) {
+			pr_err("%s: completed %li out of %u, %s\n",
+			       __func__,
+			       count - remaining, count,
+			       hv_status_to_string(status));
+			break;
+		}
+		completed = hv_repcomp(status);
+		registers += completed;
+		remaining -= completed;
+	}
+
+	local_irq_restore(flags);
+
+	return hv_status_to_errno(status);
+}
+

drivers/hv/mshv.h

@@ -0,0 +1,156 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2023, Microsoft Corporation.
+ */
+
+#ifndef _MSHV_H_
+#define _MSHV_H_
+
+#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/semaphore.h>
+#include <linux/sched.h>
+#include <linux/srcu.h>
+#include <linux/wait.h>
+#include <uapi/linux/mshv.h>
+
+/*
+ * Hyper-V hypercalls
+ */
+
+int hv_call_withdraw_memory(u64 count, int node, u64 partition_id);
+int hv_call_create_partition(
+		u64 flags,
+		struct hv_partition_creation_properties creation_properties,
+		union hv_partition_isolation_properties isolation_properties,
+		u64 *partition_id);
+int hv_call_initialize_partition(u64 partition_id);
+int hv_call_finalize_partition(u64 partition_id);
+int hv_call_delete_partition(u64 partition_id);
+int hv_call_map_gpa_pages(
+		u64 partition_id,
+		u64 gpa_target,
+		u64 page_count, u32 flags,
+		struct page **pages);
+int hv_call_unmap_gpa_pages(
+		u64 partition_id,
+		u64 gpa_target,
+		u64 page_count, u32 flags);
+int hv_call_get_vp_registers(
+		u32 vp_index,
+		u64 partition_id,
+		u16 count,
+		union hv_input_vtl input_vtl,
+		struct hv_register_assoc *registers);
+int hv_call_get_gpa_access_states(
+		u64 partition_id,
+		u32 count,
+		u64 gpa_base_pfn,
+		u64 state_flags,
+		int *written_total,
+		union hv_gpa_page_access_state *states);
+
+int hv_call_set_vp_registers(
+		u32 vp_index,
+		u64 partition_id,
+		u16 count,
+		union hv_input_vtl input_vtl,
+		struct hv_register_assoc *registers);
+int hv_call_install_intercept(u64 partition_id, u32 access_type,
+		enum hv_intercept_type intercept_type,
+		union hv_intercept_parameters intercept_parameter);
+int hv_call_assert_virtual_interrupt(
+		u64 partition_id,
+		u32 vector,
+		u64 dest_addr,
+		union hv_interrupt_control control);
+int hv_call_clear_virtual_interrupt(u64 partition_id);
+
+#ifdef HV_SUPPORTS_VP_STATE
+int hv_call_get_vp_state(
+		u32 vp_index,
+		u64 partition_id,
+		enum hv_get_set_vp_state_type type,
+		struct hv_vp_state_data_xsave xsave,
+		/* Choose between pages and ret_output */
+		u64 page_count,
+		struct page **pages,
+		union hv_output_get_vp_state *ret_output);
+int hv_call_set_vp_state(
+		u32 vp_index,
+		u64 partition_id,
+		enum hv_get_set_vp_state_type type,
+		struct hv_vp_state_data_xsave xsave,
+		/* Choose between pages and bytes */
+		u64 page_count,
+		struct page **pages,
+		u32 num_bytes,
+		u8 *bytes);
+#endif
+
+int hv_call_map_vp_state_page(u64 partition_id, u32 vp_index, u32 type,
+				struct page **state_page);
+int hv_call_unmap_vp_state_page(u64 partition_id, u32 vp_index, u32 type);
+int hv_call_get_partition_property(
+		u64 partition_id,
+		u64 property_code,
+		u64 *property_value);
+int hv_call_set_partition_property(
+	u64 partition_id, u64 property_code, u64 property_value,
+	void (*completion_handler)(void * /* data */, u64 * /* status */),
+	void *completion_data);
+int hv_call_translate_virtual_address(
+		u32 vp_index,
+		u64 partition_id,
+		u64 flags,
+		u64 gva,
+		u64 *gpa,
+		union hv_translate_gva_result *result);
+int hv_call_get_vp_cpuid_values(
+		u32 vp_index,
+		u64 partition_id,
+		union hv_get_vp_cpuid_values_flags values_flags,
+		struct hv_cpuid_leaf_info *info,
+		union hv_output_get_vp_cpuid_values *result);
+
+int hv_call_create_port(u64 port_partition_id, union hv_port_id port_id,
+			u64 connection_partition_id, struct hv_port_info *port_info,
+			u8 port_vtl, u8 min_connection_vtl, int node);
+int hv_call_delete_port(u64 port_partition_id, union hv_port_id port_id);
+int hv_call_connect_port(u64 port_partition_id, union hv_port_id port_id,
+			 u64 connection_partition_id,
+			 union hv_connection_id connection_id,
+			 struct hv_connection_info *connection_info,
+			 u8 connection_vtl, int node);
+int hv_call_disconnect_port(u64 connection_partition_id,
+			    union hv_connection_id connection_id);
+int hv_call_notify_port_ring_empty(u32 sint_index);
+#ifdef HV_SUPPORTS_REGISTER_INTERCEPT
+int hv_call_register_intercept_result(u32 vp_index,
+				  u64 partition_id,
+				  enum hv_intercept_type intercept_type,
+				  union hv_register_intercept_result_parameters *params);
+#endif
+int hv_call_signal_event_direct(u32 vp_index,
+				u64 partition_id,
+				u8 vtl,
+				u8 sint,
+				u16 flag_number,
+				u8 *newly_signaled);
+int hv_call_post_message_direct(u32 vp_index,
+				u64 partition_id,
+				u8 vtl,
+				u32 sint_index,
+				u8 *message);
+
+struct mshv_partition *mshv_partition_find(u64 partition_id) __must_hold(RCU);
+
+int mshv_xfer_to_guest_mode_handle_work(unsigned long ti_work);
+
+typedef long (*mshv_create_func_t)(void __user *user_arg);
+typedef long (*mshv_check_ext_func_t)(u32 arg);
+int mshv_setup_vtl_func(const mshv_create_func_t create_vtl,
+			const mshv_check_ext_func_t check_ext);
+int mshv_set_create_partition_func(const mshv_create_func_t func);
+
+#endif /* _MSHV_H */