Resguardo inicial

linux-7.2.3/drivers/virt/Kconfig

@@ -0,0 +1,52 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Virtualization support drivers
+#
+
+menuconfig VIRT_DRIVERS
+	bool "Virtualization drivers"
+	help
+	  Say Y here to get to see options for device drivers that support
+	  virtualization environments.
+
+	  If you say N, all options in this submenu will be skipped and disabled.
+
+if VIRT_DRIVERS
+
+config VMGENID
+	tristate "Virtual Machine Generation ID driver"
+	default y
+	help
+	  Say Y here to use the hypervisor-provided Virtual Machine Generation ID
+	  to reseed the RNG when the VM is cloned. This is highly recommended if
+	  you intend to do any rollback / cloning / snapshotting of VMs.
+
+	  Prefer Y to M so that this protection is activated very early.
+
+config FSL_HV_MANAGER
+	tristate "Freescale hypervisor management driver"
+	depends on FSL_SOC
+	select EPAPR_PARAVIRT
+	help
+          The Freescale hypervisor management driver provides several services
+	  to drivers and applications related to the Freescale hypervisor:
+
+          1) An ioctl interface for querying and managing partitions.
+
+          2) A file interface to reading incoming doorbells.
+
+          3) An interrupt handler for shutting down the partition upon
+	     receiving the shutdown doorbell from a manager partition.
+
+          4) A kernel interface for receiving callbacks when a managed
+	     partition shuts down.
+
+source "drivers/virt/vboxguest/Kconfig"
+
+source "drivers/virt/nitro_enclaves/Kconfig"
+
+source "drivers/virt/acrn/Kconfig"
+
+endif
+
+source "drivers/virt/coco/Kconfig"

linux-7.2.3/drivers/virt/Makefile

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for drivers that support virtualization
+#
+
+obj-$(CONFIG_FSL_HV_MANAGER)	+= fsl_hypervisor.o
+obj-$(CONFIG_VMGENID)		+= vmgenid.o
+obj-y				+= vboxguest/
+
+obj-$(CONFIG_NITRO_ENCLAVES)	+= nitro_enclaves/
+obj-$(CONFIG_ACRN_HSM)		+= acrn/
+obj-y				+= coco/

linux-7.2.3/drivers/virt/acrn/Kconfig

@@ -0,0 +1,15 @@
+# SPDX-License-Identifier: GPL-2.0
+config ACRN_HSM
+	tristate "ACRN Hypervisor Service Module"
+	depends on ACRN_GUEST
+	select EVENTFD
+	help
+	  ACRN Hypervisor Service Module (HSM) is a kernel module which
+	  communicates with ACRN userspace through ioctls and talks to
+	  the ACRN Hypervisor through hypercalls. HSM will only run in
+	  a privileged management VM, called Service VM, to manage User
+	  VMs and do I/O emulation. Not required for simply running
+	  under ACRN as a User VM.
+
+	  To compile as a module, choose M, the module will be called
+	  acrn. If unsure, say N.

linux-7.2.3/drivers/virt/acrn/Makefile

@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_ACRN_HSM)	:= acrn.o
+acrn-y := hsm.o vm.o mm.o ioreq.o ioeventfd.o irqfd.o

linux-7.2.3/drivers/virt/acrn/acrn_drv.h

@@ -0,0 +1,229 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ACRN_HSM_DRV_H
+#define __ACRN_HSM_DRV_H
+
+#include <linux/acrn.h>
+#include <linux/dev_printk.h>
+#include <linux/miscdevice.h>
+#include <linux/types.h>
+
+#include "hypercall.h"
+
+extern struct miscdevice acrn_dev;
+
+#define ACRN_NAME_LEN		16
+#define ACRN_MEM_MAPPING_MAX	256
+
+#define ACRN_MEM_REGION_ADD	0
+#define ACRN_MEM_REGION_DEL	2
+
+struct acrn_vm;
+struct acrn_ioreq_client;
+
+/**
+ * struct vm_memory_region_op - Hypervisor memory operation
+ * @type:		Operation type (ACRN_MEM_REGION_*)
+ * @attr:		Memory attribute (ACRN_MEM_TYPE_* | ACRN_MEM_ACCESS_*)
+ * @user_vm_pa:		Physical address of User VM to be mapped.
+ * @service_vm_pa:	Physical address of Service VM to be mapped.
+ * @size:		Size of this region.
+ *
+ * Structure containing needed information that is provided to ACRN Hypervisor
+ * to manage the EPT mappings of a single memory region of the User VM. Several
+ * &struct vm_memory_region_op can be batched to ACRN Hypervisor, see &struct
+ * vm_memory_region_batch.
+ */
+struct vm_memory_region_op {
+	u32	type;
+	u32	attr;
+	u64	user_vm_pa;
+	u64	service_vm_pa;
+	u64	size;
+};
+
+/**
+ * struct vm_memory_region_batch - A batch of vm_memory_region_op.
+ * @vmid:		A User VM ID.
+ * @reserved:		Reserved.
+ * @regions_num:	The number of vm_memory_region_op.
+ * @regions_gpa:	Physical address of a vm_memory_region_op array.
+ * @regions_op:		Flexible array of vm_memory_region_op.
+ *
+ * HC_VM_SET_MEMORY_REGIONS uses this structure to manage EPT mappings of
+ * multiple memory regions of a User VM. A &struct vm_memory_region_batch
+ * contains multiple &struct vm_memory_region_op for batch processing in the
+ * ACRN Hypervisor.
+ */
+struct vm_memory_region_batch {
+	u16			   vmid;
+	u16			   reserved[3];
+	u32			   regions_num;
+	u64			   regions_gpa;
+	struct vm_memory_region_op regions_op[] __counted_by(regions_num);
+};
+
+/**
+ * struct vm_memory_mapping - Memory map between a User VM and the Service VM
+ * @pages:		Pages in Service VM kernel.
+ * @npages:		Number of pages.
+ * @service_vm_va:	Virtual address in Service VM kernel.
+ * @user_vm_pa:		Physical address in User VM.
+ * @size:		Size of this memory region.
+ *
+ * HSM maintains memory mappings between a User VM GPA and the Service VM
+ * kernel VA for accelerating the User VM GPA translation.
+ */
+struct vm_memory_mapping {
+	struct page	**pages;
+	int		npages;
+	void		*service_vm_va;
+	u64		user_vm_pa;
+	size_t		size;
+};
+
+/**
+ * struct acrn_ioreq_buffer - Data for setting the ioreq buffer of User VM
+ * @ioreq_buf:	The GPA of the IO request shared buffer of a VM
+ *
+ * The parameter for the HC_SET_IOREQ_BUFFER hypercall used to set up
+ * the shared I/O request buffer between Service VM and ACRN hypervisor.
+ */
+struct acrn_ioreq_buffer {
+	u64	ioreq_buf;
+};
+
+struct acrn_ioreq_range {
+	struct list_head	list;
+	u32			type;
+	u64			start;
+	u64			end;
+};
+
+#define ACRN_IOREQ_CLIENT_DESTROYING	0U
+typedef	int (*ioreq_handler_t)(struct acrn_ioreq_client *client,
+			       struct acrn_io_request *req);
+/**
+ * struct acrn_ioreq_client - Structure of I/O client.
+ * @name:	Client name
+ * @vm:		The VM that the client belongs to
+ * @list:	List node for this acrn_ioreq_client
+ * @is_default:	If this client is the default one
+ * @flags:	Flags (ACRN_IOREQ_CLIENT_*)
+ * @range_list:	I/O ranges
+ * @range_lock:	Lock to protect range_list
+ * @ioreqs_map:	The pending I/O requests bitmap.
+ * @handler:	I/O requests handler of this client
+ * @thread:	The thread which executes the handler
+ * @wq:		The wait queue for the handler thread parking
+ * @priv:	Data for the thread
+ */
+struct acrn_ioreq_client {
+	char			name[ACRN_NAME_LEN];
+	struct acrn_vm		*vm;
+	struct list_head	list;
+	bool			is_default;
+	unsigned long		flags;
+	struct list_head	range_list;
+	rwlock_t		range_lock;
+	DECLARE_BITMAP(ioreqs_map, ACRN_IO_REQUEST_MAX);
+	ioreq_handler_t		handler;
+	struct task_struct	*thread;
+	wait_queue_head_t	wq;
+	void			*priv;
+};
+
+#define ACRN_INVALID_VMID (0xffffU)
+
+#define ACRN_VM_FLAG_DESTROYED		0U
+#define ACRN_VM_FLAG_CLEARING_IOREQ	1U
+extern struct list_head acrn_vm_list;
+extern rwlock_t acrn_vm_list_lock;
+/**
+ * struct acrn_vm - Properties of ACRN User VM.
+ * @list:			Entry within global list of all VMs.
+ * @vmid:			User VM ID.
+ * @vcpu_num:			Number of virtual CPUs in the VM.
+ * @flags:			Flags (ACRN_VM_FLAG_*) of the VM. This is VM
+ *				flag management in HSM which is different
+ *				from the &acrn_vm_creation.vm_flag.
+ * @regions_mapping_lock:	Lock to protect &acrn_vm.regions_mapping and
+ *				&acrn_vm.regions_mapping_count.
+ * @regions_mapping:		Memory mappings of this VM.
+ * @regions_mapping_count:	Number of memory mapping of this VM.
+ * @ioreq_clients_lock:		Lock to protect ioreq_clients and default_client
+ * @ioreq_clients:		The I/O request clients list of this VM
+ * @default_client:		The default I/O request client
+ * @ioreq_buf:			I/O request shared buffer
+ * @ioreq_page:			The page of the I/O request shared buffer
+ * @pci_conf_addr:		Address of a PCI configuration access emulation
+ * @monitor_page:		Page of interrupt statistics of User VM
+ * @ioeventfds_lock:		Lock to protect ioeventfds list
+ * @ioeventfds:			List to link all hsm_ioeventfd
+ * @ioeventfd_client:		I/O client for ioeventfds of the VM
+ * @irqfds_lock:		Lock to protect irqfds list
+ * @irqfds:			List to link all hsm_irqfd
+ * @irqfd_wq:			Workqueue for irqfd async shutdown
+ */
+struct acrn_vm {
+	struct list_head		list;
+	u16				vmid;
+	int				vcpu_num;
+	unsigned long			flags;
+	struct mutex			regions_mapping_lock;
+	struct vm_memory_mapping	regions_mapping[ACRN_MEM_MAPPING_MAX];
+	int				regions_mapping_count;
+	spinlock_t			ioreq_clients_lock;
+	struct list_head		ioreq_clients;
+	struct acrn_ioreq_client	*default_client;
+	struct acrn_io_request_buffer	*ioreq_buf;
+	struct page			*ioreq_page;
+	u32				pci_conf_addr;
+	struct page			*monitor_page;
+	struct mutex			ioeventfds_lock;
+	struct list_head		ioeventfds;
+	struct acrn_ioreq_client	*ioeventfd_client;
+	struct mutex			irqfds_lock;
+	struct list_head		irqfds;
+	struct workqueue_struct		*irqfd_wq;
+};
+
+struct acrn_vm *acrn_vm_create(struct acrn_vm *vm,
+			       struct acrn_vm_creation *vm_param);
+int acrn_vm_destroy(struct acrn_vm *vm);
+int acrn_mm_region_add(struct acrn_vm *vm, u64 user_gpa, u64 service_gpa,
+		       u64 size, u32 mem_type, u32 mem_access_right);
+int acrn_mm_region_del(struct acrn_vm *vm, u64 user_gpa, u64 size);
+int acrn_vm_memseg_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap);
+int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap);
+int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap);
+void acrn_vm_all_ram_unmap(struct acrn_vm *vm);
+
+int acrn_ioreq_init(struct acrn_vm *vm, u64 buf_vma);
+void acrn_ioreq_deinit(struct acrn_vm *vm);
+int acrn_ioreq_intr_setup(void);
+void acrn_ioreq_intr_remove(void);
+void acrn_ioreq_request_clear(struct acrn_vm *vm);
+int acrn_ioreq_client_wait(struct acrn_ioreq_client *client);
+int acrn_ioreq_request_default_complete(struct acrn_vm *vm, u16 vcpu);
+struct acrn_ioreq_client *acrn_ioreq_client_create(struct acrn_vm *vm,
+						   ioreq_handler_t handler,
+						   void *data, bool is_default,
+						   const char *name);
+void acrn_ioreq_client_destroy(struct acrn_ioreq_client *client);
+int acrn_ioreq_range_add(struct acrn_ioreq_client *client,
+			 u32 type, u64 start, u64 end);
+void acrn_ioreq_range_del(struct acrn_ioreq_client *client,
+			  u32 type, u64 start, u64 end);
+
+int acrn_msi_inject(struct acrn_vm *vm, u64 msi_addr, u64 msi_data);
+
+int acrn_ioeventfd_init(struct acrn_vm *vm);
+int acrn_ioeventfd_config(struct acrn_vm *vm, struct acrn_ioeventfd *args);
+void acrn_ioeventfd_deinit(struct acrn_vm *vm);
+
+int acrn_irqfd_init(struct acrn_vm *vm);
+int acrn_irqfd_config(struct acrn_vm *vm, struct acrn_irqfd *args);
+void acrn_irqfd_deinit(struct acrn_vm *vm);
+
+#endif /* __ACRN_HSM_DRV_H */

linux-7.2.3/drivers/virt/acrn/hsm.c

@@ -0,0 +1,539 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACRN Hypervisor Service Module (HSM)
+ *
+ * Copyright (C) 2020 Intel Corporation. All rights reserved.
+ *
+ * Authors:
+ *	Fengwei Yin <fengwei.yin@intel.com>
+ *	Yakui Zhao <yakui.zhao@intel.com>
+ */
+
+#include <linux/cpu.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <asm/acrn.h>
+#include <asm/cpuid/api.h>
+#include <asm/hypervisor.h>
+
+#include "acrn_drv.h"
+
+/*
+ * When /dev/acrn_hsm is opened, a 'struct acrn_vm' object is created to
+ * represent a VM instance and continues to be associated with the opened file
+ * descriptor. All ioctl operations on this file descriptor will be targeted to
+ * the VM instance. Release of this file descriptor will destroy the object.
+ */
+static int acrn_dev_open(struct inode *inode, struct file *filp)
+{
+	struct acrn_vm *vm;
+
+	vm = kzalloc_obj(*vm);
+	if (!vm)
+		return -ENOMEM;
+
+	vm->vmid = ACRN_INVALID_VMID;
+	filp->private_data = vm;
+	return 0;
+}
+
+static int pmcmd_ioctl(u64 cmd, void __user *uptr)
+{
+	struct acrn_pstate_data *px_data;
+	struct acrn_cstate_data *cx_data;
+	u64 *pm_info;
+	int ret = 0;
+
+	switch (cmd & PMCMD_TYPE_MASK) {
+	case ACRN_PMCMD_GET_PX_CNT:
+	case ACRN_PMCMD_GET_CX_CNT:
+		pm_info = kzalloc(sizeof(u64), GFP_KERNEL);
+		if (!pm_info)
+			return -ENOMEM;
+
+		ret = hcall_get_cpu_state(cmd, virt_to_phys(pm_info));
+		if (ret < 0) {
+			kfree(pm_info);
+			break;
+		}
+
+		if (copy_to_user(uptr, pm_info, sizeof(u64)))
+			ret = -EFAULT;
+		kfree(pm_info);
+		break;
+	case ACRN_PMCMD_GET_PX_DATA:
+		px_data = kzalloc_obj(*px_data);
+		if (!px_data)
+			return -ENOMEM;
+
+		ret = hcall_get_cpu_state(cmd, virt_to_phys(px_data));
+		if (ret < 0) {
+			kfree(px_data);
+			break;
+		}
+
+		if (copy_to_user(uptr, px_data, sizeof(*px_data)))
+			ret = -EFAULT;
+		kfree(px_data);
+		break;
+	case ACRN_PMCMD_GET_CX_DATA:
+		cx_data = kzalloc_obj(*cx_data);
+		if (!cx_data)
+			return -ENOMEM;
+
+		ret = hcall_get_cpu_state(cmd, virt_to_phys(cx_data));
+		if (ret < 0) {
+			kfree(cx_data);
+			break;
+		}
+
+		if (copy_to_user(uptr, cx_data, sizeof(*cx_data)))
+			ret = -EFAULT;
+		kfree(cx_data);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+/*
+ * HSM relies on hypercall layer of the ACRN hypervisor to do the
+ * sanity check against the input parameters.
+ */
+static long acrn_dev_ioctl(struct file *filp, unsigned int cmd,
+			   unsigned long ioctl_param)
+{
+	struct acrn_vm *vm = filp->private_data;
+	struct acrn_vm_creation *vm_param;
+	struct acrn_vcpu_regs *cpu_regs;
+	struct acrn_ioreq_notify notify;
+	struct acrn_ptdev_irq *irq_info;
+	struct acrn_ioeventfd ioeventfd;
+	struct acrn_vm_memmap memmap;
+	struct acrn_mmiodev *mmiodev;
+	struct acrn_msi_entry *msi;
+	struct acrn_pcidev *pcidev;
+	struct acrn_irqfd irqfd;
+	struct acrn_vdev *vdev;
+	struct page *page;
+	u64 cstate_cmd;
+	int i, ret = 0;
+
+	if (vm->vmid == ACRN_INVALID_VMID && cmd != ACRN_IOCTL_CREATE_VM) {
+		dev_dbg(acrn_dev.this_device,
+			"ioctl 0x%x: Invalid VM state!\n", cmd);
+		return -EINVAL;
+	}
+
+	switch (cmd) {
+	case ACRN_IOCTL_CREATE_VM:
+		vm_param = memdup_user((void __user *)ioctl_param,
+				       sizeof(struct acrn_vm_creation));
+		if (IS_ERR(vm_param))
+			return PTR_ERR(vm_param);
+
+		if ((vm_param->reserved0 | vm_param->reserved1) != 0) {
+			kfree(vm_param);
+			return -EINVAL;
+		}
+
+		vm = acrn_vm_create(vm, vm_param);
+		if (!vm) {
+			ret = -EINVAL;
+			kfree(vm_param);
+			break;
+		}
+
+		if (copy_to_user((void __user *)ioctl_param, vm_param,
+				 sizeof(struct acrn_vm_creation))) {
+			acrn_vm_destroy(vm);
+			ret = -EFAULT;
+		}
+
+		kfree(vm_param);
+		break;
+	case ACRN_IOCTL_START_VM:
+		ret = hcall_start_vm(vm->vmid);
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to start VM %u!\n", vm->vmid);
+		break;
+	case ACRN_IOCTL_PAUSE_VM:
+		ret = hcall_pause_vm(vm->vmid);
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to pause VM %u!\n", vm->vmid);
+		break;
+	case ACRN_IOCTL_RESET_VM:
+		ret = hcall_reset_vm(vm->vmid);
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to restart VM %u!\n", vm->vmid);
+		break;
+	case ACRN_IOCTL_DESTROY_VM:
+		ret = acrn_vm_destroy(vm);
+		break;
+	case ACRN_IOCTL_SET_VCPU_REGS:
+		cpu_regs = memdup_user((void __user *)ioctl_param,
+				       sizeof(struct acrn_vcpu_regs));
+		if (IS_ERR(cpu_regs))
+			return PTR_ERR(cpu_regs);
+
+		for (i = 0; i < ARRAY_SIZE(cpu_regs->reserved); i++)
+			if (cpu_regs->reserved[i]) {
+				kfree(cpu_regs);
+				return -EINVAL;
+			}
+
+		for (i = 0; i < ARRAY_SIZE(cpu_regs->vcpu_regs.reserved_32); i++)
+			if (cpu_regs->vcpu_regs.reserved_32[i]) {
+				kfree(cpu_regs);
+				return -EINVAL;
+			}
+
+		for (i = 0; i < ARRAY_SIZE(cpu_regs->vcpu_regs.reserved_64); i++)
+			if (cpu_regs->vcpu_regs.reserved_64[i]) {
+				kfree(cpu_regs);
+				return -EINVAL;
+			}
+
+		for (i = 0; i < ARRAY_SIZE(cpu_regs->vcpu_regs.gdt.reserved); i++)
+			if (cpu_regs->vcpu_regs.gdt.reserved[i] |
+			    cpu_regs->vcpu_regs.idt.reserved[i]) {
+				kfree(cpu_regs);
+				return -EINVAL;
+			}
+
+		ret = hcall_set_vcpu_regs(vm->vmid, virt_to_phys(cpu_regs));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to set regs state of VM%u!\n",
+				vm->vmid);
+		kfree(cpu_regs);
+		break;
+	case ACRN_IOCTL_SET_MEMSEG:
+		if (copy_from_user(&memmap, (void __user *)ioctl_param,
+				   sizeof(memmap)))
+			return -EFAULT;
+
+		ret = acrn_vm_memseg_map(vm, &memmap);
+		break;
+	case ACRN_IOCTL_UNSET_MEMSEG:
+		if (copy_from_user(&memmap, (void __user *)ioctl_param,
+				   sizeof(memmap)))
+			return -EFAULT;
+
+		ret = acrn_vm_memseg_unmap(vm, &memmap);
+		break;
+	case ACRN_IOCTL_ASSIGN_MMIODEV:
+		mmiodev = memdup_user((void __user *)ioctl_param,
+				      sizeof(struct acrn_mmiodev));
+		if (IS_ERR(mmiodev))
+			return PTR_ERR(mmiodev);
+
+		ret = hcall_assign_mmiodev(vm->vmid, virt_to_phys(mmiodev));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to assign MMIO device!\n");
+		kfree(mmiodev);
+		break;
+	case ACRN_IOCTL_DEASSIGN_MMIODEV:
+		mmiodev = memdup_user((void __user *)ioctl_param,
+				      sizeof(struct acrn_mmiodev));
+		if (IS_ERR(mmiodev))
+			return PTR_ERR(mmiodev);
+
+		ret = hcall_deassign_mmiodev(vm->vmid, virt_to_phys(mmiodev));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to deassign MMIO device!\n");
+		kfree(mmiodev);
+		break;
+	case ACRN_IOCTL_ASSIGN_PCIDEV:
+		pcidev = memdup_user((void __user *)ioctl_param,
+				     sizeof(struct acrn_pcidev));
+		if (IS_ERR(pcidev))
+			return PTR_ERR(pcidev);
+
+		ret = hcall_assign_pcidev(vm->vmid, virt_to_phys(pcidev));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to assign pci device!\n");
+		kfree(pcidev);
+		break;
+	case ACRN_IOCTL_DEASSIGN_PCIDEV:
+		pcidev = memdup_user((void __user *)ioctl_param,
+				     sizeof(struct acrn_pcidev));
+		if (IS_ERR(pcidev))
+			return PTR_ERR(pcidev);
+
+		ret = hcall_deassign_pcidev(vm->vmid, virt_to_phys(pcidev));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to deassign pci device!\n");
+		kfree(pcidev);
+		break;
+	case ACRN_IOCTL_CREATE_VDEV:
+		vdev = memdup_user((void __user *)ioctl_param,
+				   sizeof(struct acrn_vdev));
+		if (IS_ERR(vdev))
+			return PTR_ERR(vdev);
+
+		ret = hcall_create_vdev(vm->vmid, virt_to_phys(vdev));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to create virtual device!\n");
+		kfree(vdev);
+		break;
+	case ACRN_IOCTL_DESTROY_VDEV:
+		vdev = memdup_user((void __user *)ioctl_param,
+				   sizeof(struct acrn_vdev));
+		if (IS_ERR(vdev))
+			return PTR_ERR(vdev);
+		ret = hcall_destroy_vdev(vm->vmid, virt_to_phys(vdev));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to destroy virtual device!\n");
+		kfree(vdev);
+		break;
+	case ACRN_IOCTL_SET_PTDEV_INTR:
+		irq_info = memdup_user((void __user *)ioctl_param,
+				       sizeof(struct acrn_ptdev_irq));
+		if (IS_ERR(irq_info))
+			return PTR_ERR(irq_info);
+
+		ret = hcall_set_ptdev_intr(vm->vmid, virt_to_phys(irq_info));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to configure intr for ptdev!\n");
+		kfree(irq_info);
+		break;
+	case ACRN_IOCTL_RESET_PTDEV_INTR:
+		irq_info = memdup_user((void __user *)ioctl_param,
+				       sizeof(struct acrn_ptdev_irq));
+		if (IS_ERR(irq_info))
+			return PTR_ERR(irq_info);
+
+		ret = hcall_reset_ptdev_intr(vm->vmid, virt_to_phys(irq_info));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to reset intr for ptdev!\n");
+		kfree(irq_info);
+		break;
+	case ACRN_IOCTL_SET_IRQLINE:
+		ret = hcall_set_irqline(vm->vmid, ioctl_param);
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to set interrupt line!\n");
+		break;
+	case ACRN_IOCTL_INJECT_MSI:
+		msi = memdup_user((void __user *)ioctl_param,
+				  sizeof(struct acrn_msi_entry));
+		if (IS_ERR(msi))
+			return PTR_ERR(msi);
+
+		ret = hcall_inject_msi(vm->vmid, virt_to_phys(msi));
+		if (ret < 0)
+			dev_dbg(acrn_dev.this_device,
+				"Failed to inject MSI!\n");
+		kfree(msi);
+		break;
+	case ACRN_IOCTL_VM_INTR_MONITOR:
+		ret = pin_user_pages_fast(ioctl_param, 1,
+					  FOLL_WRITE | FOLL_LONGTERM, &page);
+		if (unlikely(ret != 1)) {
+			dev_dbg(acrn_dev.this_device,
+				"Failed to pin intr hdr buffer!\n");
+			return -EFAULT;
+		}
+
+		ret = hcall_vm_intr_monitor(vm->vmid, page_to_phys(page));
+		if (ret < 0) {
+			unpin_user_page(page);
+			dev_dbg(acrn_dev.this_device,
+				"Failed to monitor intr data!\n");
+			return ret;
+		}
+		if (vm->monitor_page)
+			unpin_user_page(vm->monitor_page);
+		vm->monitor_page = page;
+		break;
+	case ACRN_IOCTL_CREATE_IOREQ_CLIENT:
+		if (vm->default_client)
+			return -EEXIST;
+		if (!acrn_ioreq_client_create(vm, NULL, NULL, true, "acrndm"))
+			ret = -EINVAL;
+		break;
+	case ACRN_IOCTL_DESTROY_IOREQ_CLIENT:
+		if (vm->default_client)
+			acrn_ioreq_client_destroy(vm->default_client);
+		break;
+	case ACRN_IOCTL_ATTACH_IOREQ_CLIENT:
+		if (vm->default_client)
+			ret = acrn_ioreq_client_wait(vm->default_client);
+		else
+			ret = -ENODEV;
+		break;
+	case ACRN_IOCTL_NOTIFY_REQUEST_FINISH:
+		if (copy_from_user(&notify, (void __user *)ioctl_param,
+				   sizeof(struct acrn_ioreq_notify)))
+			return -EFAULT;
+
+		if (notify.reserved != 0)
+			return -EINVAL;
+
+		ret = acrn_ioreq_request_default_complete(vm, notify.vcpu);
+		break;
+	case ACRN_IOCTL_CLEAR_VM_IOREQ:
+		acrn_ioreq_request_clear(vm);
+		break;
+	case ACRN_IOCTL_PM_GET_CPU_STATE:
+		if (copy_from_user(&cstate_cmd, (void __user *)ioctl_param,
+				   sizeof(cstate_cmd)))
+			return -EFAULT;
+
+		ret = pmcmd_ioctl(cstate_cmd, (void __user *)ioctl_param);
+		break;
+	case ACRN_IOCTL_IOEVENTFD:
+		if (copy_from_user(&ioeventfd, (void __user *)ioctl_param,
+				   sizeof(ioeventfd)))
+			return -EFAULT;
+
+		if (ioeventfd.reserved != 0)
+			return -EINVAL;
+
+		ret = acrn_ioeventfd_config(vm, &ioeventfd);
+		break;
+	case ACRN_IOCTL_IRQFD:
+		if (copy_from_user(&irqfd, (void __user *)ioctl_param,
+				   sizeof(irqfd)))
+			return -EFAULT;
+		ret = acrn_irqfd_config(vm, &irqfd);
+		break;
+	default:
+		dev_dbg(acrn_dev.this_device, "Unknown IOCTL 0x%x!\n", cmd);
+		ret = -ENOTTY;
+	}
+
+	return ret;
+}
+
+static int acrn_dev_release(struct inode *inode, struct file *filp)
+{
+	struct acrn_vm *vm = filp->private_data;
+
+	acrn_vm_destroy(vm);
+	kfree(vm);
+	return 0;
+}
+
+static ssize_t remove_cpu_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	u64 cpu, lapicid;
+	int ret;
+
+	if (kstrtoull(buf, 0, &cpu) < 0)
+		return -EINVAL;
+
+	if (cpu >= num_possible_cpus() || cpu == 0 || !cpu_is_hotpluggable(cpu))
+		return -EINVAL;
+
+	if (cpu_online(cpu))
+		remove_cpu(cpu);
+
+	lapicid = cpu_data(cpu).topo.apicid;
+	dev_dbg(dev, "Try to remove cpu %lld with lapicid %lld\n", cpu, lapicid);
+	ret = hcall_sos_remove_cpu(lapicid);
+	if (ret < 0) {
+		dev_err(dev, "Failed to remove cpu %lld!\n", cpu);
+		goto fail_remove;
+	}
+
+	return count;
+
+fail_remove:
+	add_cpu(cpu);
+	return ret;
+}
+static DEVICE_ATTR_WO(remove_cpu);
+
+static umode_t acrn_attr_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+       if (a == &dev_attr_remove_cpu.attr)
+               return IS_ENABLED(CONFIG_HOTPLUG_CPU) ? a->mode : 0;
+
+       return a->mode;
+}
+
+static struct attribute *acrn_attrs[] = {
+	&dev_attr_remove_cpu.attr,
+	NULL
+};
+
+static struct attribute_group acrn_attr_group = {
+	.attrs = acrn_attrs,
+	.is_visible = acrn_attr_visible,
+};
+
+static const struct attribute_group *acrn_attr_groups[] = {
+	&acrn_attr_group,
+	NULL
+};
+
+static const struct file_operations acrn_fops = {
+	.owner		= THIS_MODULE,
+	.open		= acrn_dev_open,
+	.release	= acrn_dev_release,
+	.unlocked_ioctl = acrn_dev_ioctl,
+};
+
+struct miscdevice acrn_dev = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "acrn_hsm",
+	.fops	= &acrn_fops,
+	.groups	= acrn_attr_groups,
+};
+
+static int __init hsm_init(void)
+{
+	int ret;
+
+	if (x86_hyper_type != X86_HYPER_ACRN)
+		return -ENODEV;
+
+	if (!(cpuid_eax(ACRN_CPUID_FEATURES) & ACRN_FEATURE_PRIVILEGED_VM))
+		return -EPERM;
+
+	ret = misc_register(&acrn_dev);
+	if (ret) {
+		pr_err("Create misc dev failed!\n");
+		return ret;
+	}
+
+	ret = acrn_ioreq_intr_setup();
+	if (ret) {
+		pr_err("Setup I/O request handler failed!\n");
+		misc_deregister(&acrn_dev);
+		return ret;
+	}
+	return 0;
+}
+
+static void __exit hsm_exit(void)
+{
+	acrn_ioreq_intr_remove();
+	misc_deregister(&acrn_dev);
+}
+module_init(hsm_init);
+module_exit(hsm_exit);
+
+MODULE_AUTHOR("Intel Corporation");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ACRN Hypervisor Service Module (HSM)");

linux-7.2.3/drivers/virt/acrn/hypercall.h

@@ -0,0 +1,306 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * ACRN HSM: hypercalls of ACRN Hypervisor
+ */
+#ifndef __ACRN_HSM_HYPERCALL_H
+#define __ACRN_HSM_HYPERCALL_H
+#include <asm/acrn.h>
+
+/*
+ * Hypercall IDs of the ACRN Hypervisor
+ */
+#define _HC_ID(x, y) (((x) << 24) | (y))
+
+#define HC_ID 0x80UL
+
+#define HC_ID_GEN_BASE			0x0UL
+#define HC_SOS_REMOVE_CPU		_HC_ID(HC_ID, HC_ID_GEN_BASE + 0x01)
+
+#define HC_ID_VM_BASE			0x10UL
+#define HC_CREATE_VM			_HC_ID(HC_ID, HC_ID_VM_BASE + 0x00)
+#define HC_DESTROY_VM			_HC_ID(HC_ID, HC_ID_VM_BASE + 0x01)
+#define HC_START_VM			_HC_ID(HC_ID, HC_ID_VM_BASE + 0x02)
+#define HC_PAUSE_VM			_HC_ID(HC_ID, HC_ID_VM_BASE + 0x03)
+#define HC_RESET_VM			_HC_ID(HC_ID, HC_ID_VM_BASE + 0x05)
+#define HC_SET_VCPU_REGS		_HC_ID(HC_ID, HC_ID_VM_BASE + 0x06)
+
+#define HC_ID_IRQ_BASE			0x20UL
+#define HC_INJECT_MSI			_HC_ID(HC_ID, HC_ID_IRQ_BASE + 0x03)
+#define HC_VM_INTR_MONITOR		_HC_ID(HC_ID, HC_ID_IRQ_BASE + 0x04)
+#define HC_SET_IRQLINE			_HC_ID(HC_ID, HC_ID_IRQ_BASE + 0x05)
+
+#define HC_ID_IOREQ_BASE		0x30UL
+#define HC_SET_IOREQ_BUFFER		_HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x00)
+#define HC_NOTIFY_REQUEST_FINISH	_HC_ID(HC_ID, HC_ID_IOREQ_BASE + 0x01)
+
+#define HC_ID_MEM_BASE			0x40UL
+#define HC_VM_SET_MEMORY_REGIONS	_HC_ID(HC_ID, HC_ID_MEM_BASE + 0x02)
+
+#define HC_ID_PCI_BASE			0x50UL
+#define HC_SET_PTDEV_INTR		_HC_ID(HC_ID, HC_ID_PCI_BASE + 0x03)
+#define HC_RESET_PTDEV_INTR		_HC_ID(HC_ID, HC_ID_PCI_BASE + 0x04)
+#define HC_ASSIGN_PCIDEV		_HC_ID(HC_ID, HC_ID_PCI_BASE + 0x05)
+#define HC_DEASSIGN_PCIDEV		_HC_ID(HC_ID, HC_ID_PCI_BASE + 0x06)
+#define HC_ASSIGN_MMIODEV		_HC_ID(HC_ID, HC_ID_PCI_BASE + 0x07)
+#define HC_DEASSIGN_MMIODEV		_HC_ID(HC_ID, HC_ID_PCI_BASE + 0x08)
+#define HC_CREATE_VDEV			_HC_ID(HC_ID, HC_ID_PCI_BASE + 0x09)
+#define HC_DESTROY_VDEV			_HC_ID(HC_ID, HC_ID_PCI_BASE + 0x0A)
+
+#define HC_ID_PM_BASE			0x80UL
+#define HC_PM_GET_CPU_STATE		_HC_ID(HC_ID, HC_ID_PM_BASE + 0x00)
+
+/**
+ * hcall_sos_remove_cpu() - Remove a vCPU of Service VM
+ * @cpu: The vCPU to be removed
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_sos_remove_cpu(u64 cpu)
+{
+	return acrn_hypercall1(HC_SOS_REMOVE_CPU, cpu);
+}
+
+/**
+ * hcall_create_vm() - Create a User VM
+ * @vminfo:	Service VM GPA of info of User VM creation
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_create_vm(u64 vminfo)
+{
+	return acrn_hypercall1(HC_CREATE_VM, vminfo);
+}
+
+/**
+ * hcall_start_vm() - Start a User VM
+ * @vmid:	User VM ID
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_start_vm(u64 vmid)
+{
+	return acrn_hypercall1(HC_START_VM, vmid);
+}
+
+/**
+ * hcall_pause_vm() - Pause a User VM
+ * @vmid:	User VM ID
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_pause_vm(u64 vmid)
+{
+	return acrn_hypercall1(HC_PAUSE_VM, vmid);
+}
+
+/**
+ * hcall_destroy_vm() - Destroy a User VM
+ * @vmid:	User VM ID
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_destroy_vm(u64 vmid)
+{
+	return acrn_hypercall1(HC_DESTROY_VM, vmid);
+}
+
+/**
+ * hcall_reset_vm() - Reset a User VM
+ * @vmid:	User VM ID
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_reset_vm(u64 vmid)
+{
+	return acrn_hypercall1(HC_RESET_VM, vmid);
+}
+
+/**
+ * hcall_set_vcpu_regs() - Set up registers of virtual CPU of a User VM
+ * @vmid:	User VM ID
+ * @regs_state:	Service VM GPA of registers state
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_set_vcpu_regs(u64 vmid, u64 regs_state)
+{
+	return acrn_hypercall2(HC_SET_VCPU_REGS, vmid, regs_state);
+}
+
+/**
+ * hcall_inject_msi() - Deliver a MSI interrupt to a User VM
+ * @vmid:	User VM ID
+ * @msi:	Service VM GPA of MSI message
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_inject_msi(u64 vmid, u64 msi)
+{
+	return acrn_hypercall2(HC_INJECT_MSI, vmid, msi);
+}
+
+/**
+ * hcall_vm_intr_monitor() - Set a shared page for User VM interrupt statistics
+ * @vmid:	User VM ID
+ * @addr:	Service VM GPA of the shared page
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_vm_intr_monitor(u64 vmid, u64 addr)
+{
+	return acrn_hypercall2(HC_VM_INTR_MONITOR, vmid, addr);
+}
+
+/**
+ * hcall_set_irqline() - Set or clear an interrupt line
+ * @vmid:	User VM ID
+ * @op:		Service VM GPA of interrupt line operations
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_set_irqline(u64 vmid, u64 op)
+{
+	return acrn_hypercall2(HC_SET_IRQLINE, vmid, op);
+}
+
+/**
+ * hcall_set_ioreq_buffer() - Set up the shared buffer for I/O Requests.
+ * @vmid:	User VM ID
+ * @buffer:	Service VM GPA of the shared buffer
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_set_ioreq_buffer(u64 vmid, u64 buffer)
+{
+	return acrn_hypercall2(HC_SET_IOREQ_BUFFER, vmid, buffer);
+}
+
+/**
+ * hcall_notify_req_finish() - Notify ACRN Hypervisor of I/O request completion.
+ * @vmid:	User VM ID
+ * @vcpu:	The vCPU which initiated the I/O request
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_notify_req_finish(u64 vmid, u64 vcpu)
+{
+	return acrn_hypercall2(HC_NOTIFY_REQUEST_FINISH, vmid, vcpu);
+}
+
+/**
+ * hcall_set_memory_regions() - Inform the hypervisor to set up EPT mappings
+ * @regions_pa:	Service VM GPA of &struct vm_memory_region_batch
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_set_memory_regions(u64 regions_pa)
+{
+	return acrn_hypercall1(HC_VM_SET_MEMORY_REGIONS, regions_pa);
+}
+
+/**
+ * hcall_create_vdev() - Create a virtual device for a User VM
+ * @vmid:	User VM ID
+ * @addr:	Service VM GPA of the &struct acrn_vdev
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_create_vdev(u64 vmid, u64 addr)
+{
+	return acrn_hypercall2(HC_CREATE_VDEV, vmid, addr);
+}
+
+/**
+ * hcall_destroy_vdev() - Destroy a virtual device of a User VM
+ * @vmid:	User VM ID
+ * @addr:	Service VM GPA of the &struct acrn_vdev
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_destroy_vdev(u64 vmid, u64 addr)
+{
+	return acrn_hypercall2(HC_DESTROY_VDEV, vmid, addr);
+}
+
+/**
+ * hcall_assign_mmiodev() - Assign a MMIO device to a User VM
+ * @vmid:	User VM ID
+ * @addr:	Service VM GPA of the &struct acrn_mmiodev
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_assign_mmiodev(u64 vmid, u64 addr)
+{
+	return acrn_hypercall2(HC_ASSIGN_MMIODEV, vmid, addr);
+}
+
+/**
+ * hcall_deassign_mmiodev() - De-assign a PCI device from a User VM
+ * @vmid:	User VM ID
+ * @addr:	Service VM GPA of the &struct acrn_mmiodev
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_deassign_mmiodev(u64 vmid, u64 addr)
+{
+	return acrn_hypercall2(HC_DEASSIGN_MMIODEV, vmid, addr);
+}
+
+/**
+ * hcall_assign_pcidev() - Assign a PCI device to a User VM
+ * @vmid:	User VM ID
+ * @addr:	Service VM GPA of the &struct acrn_pcidev
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_assign_pcidev(u64 vmid, u64 addr)
+{
+	return acrn_hypercall2(HC_ASSIGN_PCIDEV, vmid, addr);
+}
+
+/**
+ * hcall_deassign_pcidev() - De-assign a PCI device from a User VM
+ * @vmid:	User VM ID
+ * @addr:	Service VM GPA of the &struct acrn_pcidev
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_deassign_pcidev(u64 vmid, u64 addr)
+{
+	return acrn_hypercall2(HC_DEASSIGN_PCIDEV, vmid, addr);
+}
+
+/**
+ * hcall_set_ptdev_intr() - Configure an interrupt for an assigned PCI device.
+ * @vmid:	User VM ID
+ * @irq:	Service VM GPA of the &struct acrn_ptdev_irq
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_set_ptdev_intr(u64 vmid, u64 irq)
+{
+	return acrn_hypercall2(HC_SET_PTDEV_INTR, vmid, irq);
+}
+
+/**
+ * hcall_reset_ptdev_intr() - Reset an interrupt for an assigned PCI device.
+ * @vmid:	User VM ID
+ * @irq:	Service VM GPA of the &struct acrn_ptdev_irq
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static inline long hcall_reset_ptdev_intr(u64 vmid, u64 irq)
+{
+	return acrn_hypercall2(HC_RESET_PTDEV_INTR, vmid, irq);
+}
+
+/*
+ * hcall_get_cpu_state() - Get P-states and C-states info from the hypervisor
+ * @state:	Service VM GPA of buffer of P-states and C-states
+ */
+static inline long hcall_get_cpu_state(u64 cmd, u64 state)
+{
+	return acrn_hypercall2(HC_PM_GET_CPU_STATE, cmd, state);
+}
+
+#endif /* __ACRN_HSM_HYPERCALL_H */

linux-7.2.3/drivers/virt/acrn/ioeventfd.c

@@ -0,0 +1,273 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACRN HSM eventfd - use eventfd objects to signal expected I/O requests
+ *
+ * Copyright (C) 2020 Intel Corporation. All rights reserved.
+ *
+ * Authors:
+ *	Shuo Liu <shuo.a.liu@intel.com>
+ *	Yakui Zhao <yakui.zhao@intel.com>
+ */
+
+#include <linux/eventfd.h>
+#include <linux/slab.h>
+
+#include "acrn_drv.h"
+
+/**
+ * struct hsm_ioeventfd - Properties of HSM ioeventfd
+ * @list:	Entry within &acrn_vm.ioeventfds of ioeventfds of a VM
+ * @eventfd:	Eventfd of the HSM ioeventfd
+ * @addr:	Address of I/O range
+ * @data:	Data for matching
+ * @length:	Length of I/O range
+ * @type:	Type of I/O range (ACRN_IOREQ_TYPE_MMIO/ACRN_IOREQ_TYPE_PORTIO)
+ * @wildcard:	Data matching or not
+ */
+struct hsm_ioeventfd {
+	struct list_head	list;
+	struct eventfd_ctx	*eventfd;
+	u64			addr;
+	u64			data;
+	int			length;
+	int			type;
+	bool			wildcard;
+};
+
+static inline int ioreq_type_from_flags(int flags)
+{
+	return flags & ACRN_IOEVENTFD_FLAG_PIO ?
+		       ACRN_IOREQ_TYPE_PORTIO : ACRN_IOREQ_TYPE_MMIO;
+}
+
+static void acrn_ioeventfd_shutdown(struct acrn_vm *vm, struct hsm_ioeventfd *p)
+{
+	lockdep_assert_held(&vm->ioeventfds_lock);
+
+	eventfd_ctx_put(p->eventfd);
+	list_del(&p->list);
+	kfree(p);
+}
+
+static bool hsm_ioeventfd_is_conflict(struct acrn_vm *vm,
+				      struct hsm_ioeventfd *ioeventfd)
+{
+	struct hsm_ioeventfd *p;
+
+	lockdep_assert_held(&vm->ioeventfds_lock);
+
+	/* Either one is wildcard, the data matching will be skipped. */
+	list_for_each_entry(p, &vm->ioeventfds, list)
+		if (p->eventfd == ioeventfd->eventfd &&
+		    p->addr == ioeventfd->addr &&
+		    p->type == ioeventfd->type &&
+		    (p->wildcard || ioeventfd->wildcard ||
+			p->data == ioeventfd->data))
+			return true;
+
+	return false;
+}
+
+/*
+ * Assign an eventfd to a VM and create a HSM ioeventfd associated with the
+ * eventfd. The properties of the HSM ioeventfd are built from a &struct
+ * acrn_ioeventfd.
+ */
+static int acrn_ioeventfd_assign(struct acrn_vm *vm,
+				 struct acrn_ioeventfd *args)
+{
+	struct eventfd_ctx *eventfd;
+	struct hsm_ioeventfd *p;
+	int ret;
+
+	/* Check for range overflow */
+	if (args->addr + args->len < args->addr)
+		return -EINVAL;
+
+	/*
+	 * Currently, acrn_ioeventfd is used to support vhost. 1,2,4,8 width
+	 * accesses can cover vhost's requirements.
+	 */
+	if (!(args->len == 1 || args->len == 2 ||
+	      args->len == 4 || args->len == 8))
+		return -EINVAL;
+
+	eventfd = eventfd_ctx_fdget(args->fd);
+	if (IS_ERR(eventfd))
+		return PTR_ERR(eventfd);
+
+	p = kzalloc_obj(*p);
+	if (!p) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	INIT_LIST_HEAD(&p->list);
+	p->addr = args->addr;
+	p->length = args->len;
+	p->eventfd = eventfd;
+	p->type = ioreq_type_from_flags(args->flags);
+
+	/*
+	 * ACRN_IOEVENTFD_FLAG_DATAMATCH flag is set in virtio 1.0 support, the
+	 * writing of notification register of each virtqueue may trigger the
+	 * notification. There is no data matching requirement.
+	 */
+	if (args->flags & ACRN_IOEVENTFD_FLAG_DATAMATCH)
+		p->data = args->data;
+	else
+		p->wildcard = true;
+
+	mutex_lock(&vm->ioeventfds_lock);
+
+	if (hsm_ioeventfd_is_conflict(vm, p)) {
+		ret = -EEXIST;
+		goto unlock_fail;
+	}
+
+	/* register the I/O range into ioreq client */
+	ret = acrn_ioreq_range_add(vm->ioeventfd_client, p->type,
+				   p->addr, p->addr + p->length - 1);
+	if (ret < 0)
+		goto unlock_fail;
+
+	list_add_tail(&p->list, &vm->ioeventfds);
+	mutex_unlock(&vm->ioeventfds_lock);
+
+	return 0;
+
+unlock_fail:
+	mutex_unlock(&vm->ioeventfds_lock);
+	kfree(p);
+fail:
+	eventfd_ctx_put(eventfd);
+	return ret;
+}
+
+static int acrn_ioeventfd_deassign(struct acrn_vm *vm,
+				   struct acrn_ioeventfd *args)
+{
+	struct hsm_ioeventfd *p;
+	struct eventfd_ctx *eventfd;
+
+	eventfd = eventfd_ctx_fdget(args->fd);
+	if (IS_ERR(eventfd))
+		return PTR_ERR(eventfd);
+
+	mutex_lock(&vm->ioeventfds_lock);
+	list_for_each_entry(p, &vm->ioeventfds, list) {
+		if (p->eventfd != eventfd)
+			continue;
+
+		acrn_ioreq_range_del(vm->ioeventfd_client, p->type,
+				     p->addr, p->addr + p->length - 1);
+		acrn_ioeventfd_shutdown(vm, p);
+		break;
+	}
+	mutex_unlock(&vm->ioeventfds_lock);
+
+	eventfd_ctx_put(eventfd);
+	return 0;
+}
+
+static struct hsm_ioeventfd *hsm_ioeventfd_match(struct acrn_vm *vm, u64 addr,
+						 u64 data, int len, int type)
+{
+	struct hsm_ioeventfd *p = NULL;
+
+	lockdep_assert_held(&vm->ioeventfds_lock);
+
+	list_for_each_entry(p, &vm->ioeventfds, list) {
+		if (p->type == type && p->addr == addr && p->length >= len &&
+		    (p->wildcard || p->data == data))
+			return p;
+	}
+
+	return NULL;
+}
+
+static int acrn_ioeventfd_handler(struct acrn_ioreq_client *client,
+				  struct acrn_io_request *req)
+{
+	struct hsm_ioeventfd *p;
+	u64 addr, val;
+	int size;
+
+	if (req->type == ACRN_IOREQ_TYPE_MMIO) {
+		/*
+		 * I/O requests are dispatched by range check only, so a
+		 * acrn_ioreq_client need process both READ and WRITE accesses
+		 * of same range. READ accesses are safe to be ignored here
+		 * because virtio PCI devices write the notify registers for
+		 * notification.
+		 */
+		if (req->reqs.mmio_request.direction == ACRN_IOREQ_DIR_READ) {
+			/* reading does nothing and return 0 */
+			req->reqs.mmio_request.value = 0;
+			return 0;
+		}
+		addr = req->reqs.mmio_request.address;
+		size = req->reqs.mmio_request.size;
+		val = req->reqs.mmio_request.value;
+	} else {
+		if (req->reqs.pio_request.direction == ACRN_IOREQ_DIR_READ) {
+			/* reading does nothing and return 0 */
+			req->reqs.pio_request.value = 0;
+			return 0;
+		}
+		addr = req->reqs.pio_request.address;
+		size = req->reqs.pio_request.size;
+		val = req->reqs.pio_request.value;
+	}
+
+	mutex_lock(&client->vm->ioeventfds_lock);
+	p = hsm_ioeventfd_match(client->vm, addr, val, size, req->type);
+	if (p)
+		eventfd_signal(p->eventfd);
+	mutex_unlock(&client->vm->ioeventfds_lock);
+
+	return 0;
+}
+
+int acrn_ioeventfd_config(struct acrn_vm *vm, struct acrn_ioeventfd *args)
+{
+	int ret;
+
+	if (args->flags & ACRN_IOEVENTFD_FLAG_DEASSIGN)
+		ret = acrn_ioeventfd_deassign(vm, args);
+	else
+		ret = acrn_ioeventfd_assign(vm, args);
+
+	return ret;
+}
+
+int acrn_ioeventfd_init(struct acrn_vm *vm)
+{
+	char name[ACRN_NAME_LEN];
+
+	mutex_init(&vm->ioeventfds_lock);
+	INIT_LIST_HEAD(&vm->ioeventfds);
+	snprintf(name, sizeof(name), "ioeventfd-%u", vm->vmid);
+	vm->ioeventfd_client = acrn_ioreq_client_create(vm,
+							acrn_ioeventfd_handler,
+							NULL, false, name);
+	if (!vm->ioeventfd_client) {
+		dev_err(acrn_dev.this_device, "Failed to create ioeventfd ioreq client!\n");
+		return -EINVAL;
+	}
+
+	dev_dbg(acrn_dev.this_device, "VM %u ioeventfd init.\n", vm->vmid);
+	return 0;
+}
+
+void acrn_ioeventfd_deinit(struct acrn_vm *vm)
+{
+	struct hsm_ioeventfd *p, *next;
+
+	dev_dbg(acrn_dev.this_device, "VM %u ioeventfd deinit.\n", vm->vmid);
+	acrn_ioreq_client_destroy(vm->ioeventfd_client);
+	mutex_lock(&vm->ioeventfds_lock);
+	list_for_each_entry_safe(p, next, &vm->ioeventfds, list)
+		acrn_ioeventfd_shutdown(vm, p);
+	mutex_unlock(&vm->ioeventfds_lock);
+}

linux-7.2.3/drivers/virt/acrn/ioreq.c

@@ -0,0 +1,652 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACRN_HSM: Handle I/O requests
+ *
+ * Copyright (C) 2020 Intel Corporation. All rights reserved.
+ *
+ * Authors:
+ *	Jason Chen CJ <jason.cj.chen@intel.com>
+ *	Fengwei Yin <fengwei.yin@intel.com>
+ */
+
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kthread.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include <asm/acrn.h>
+
+#include "acrn_drv.h"
+
+static void ioreq_pause(void);
+static void ioreq_resume(void);
+
+static void ioreq_dispatcher(struct work_struct *work);
+static struct workqueue_struct *ioreq_wq;
+static DECLARE_WORK(ioreq_work, ioreq_dispatcher);
+
+static inline bool has_pending_request(struct acrn_ioreq_client *client)
+{
+	return !bitmap_empty(client->ioreqs_map, ACRN_IO_REQUEST_MAX);
+}
+
+static inline bool is_destroying(struct acrn_ioreq_client *client)
+{
+	return test_bit(ACRN_IOREQ_CLIENT_DESTROYING, &client->flags);
+}
+
+static int ioreq_complete_request(struct acrn_vm *vm, u16 vcpu,
+				  struct acrn_io_request *acrn_req)
+{
+	bool polling_mode;
+	int ret = 0;
+
+	polling_mode = acrn_req->completion_polling;
+	/* Add barrier() to make sure the writes are done before completion */
+	smp_store_release(&acrn_req->processed, ACRN_IOREQ_STATE_COMPLETE);
+
+	/*
+	 * To fulfill the requirement of real-time in several industry
+	 * scenarios, like automotive, ACRN can run under the partition mode,
+	 * in which User VMs and Service VM are bound to dedicated CPU cores.
+	 * Polling mode of handling the I/O request is introduced to achieve a
+	 * faster I/O request handling. In polling mode, the hypervisor polls
+	 * I/O request's completion. Once an I/O request is marked as
+	 * ACRN_IOREQ_STATE_COMPLETE, hypervisor resumes from the polling point
+	 * to continue the I/O request flow. Thus, the completion notification
+	 * from HSM of I/O request is not needed.  Please note,
+	 * completion_polling needs to be read before the I/O request being
+	 * marked as ACRN_IOREQ_STATE_COMPLETE to avoid racing with the
+	 * hypervisor.
+	 */
+	if (!polling_mode) {
+		ret = hcall_notify_req_finish(vm->vmid, vcpu);
+		if (ret < 0)
+			dev_err(acrn_dev.this_device,
+				"Notify I/O request finished failed!\n");
+	}
+
+	return ret;
+}
+
+static int acrn_ioreq_complete_request(struct acrn_ioreq_client *client,
+				       u16 vcpu,
+				       struct acrn_io_request *acrn_req)
+{
+	int ret;
+
+	if (vcpu >= client->vm->vcpu_num)
+		return -EINVAL;
+
+	clear_bit(vcpu, client->ioreqs_map);
+	if (!acrn_req) {
+		acrn_req = (struct acrn_io_request *)client->vm->ioreq_buf;
+		acrn_req += vcpu;
+	}
+
+	ret = ioreq_complete_request(client->vm, vcpu, acrn_req);
+
+	return ret;
+}
+
+int acrn_ioreq_request_default_complete(struct acrn_vm *vm, u16 vcpu)
+{
+	int ret = 0;
+
+	spin_lock_bh(&vm->ioreq_clients_lock);
+	if (vm->default_client)
+		ret = acrn_ioreq_complete_request(vm->default_client,
+						  vcpu, NULL);
+	spin_unlock_bh(&vm->ioreq_clients_lock);
+
+	return ret;
+}
+
+/**
+ * acrn_ioreq_range_add() - Add an iorange monitored by an ioreq client
+ * @client:	The ioreq client
+ * @type:	Type (ACRN_IOREQ_TYPE_MMIO or ACRN_IOREQ_TYPE_PORTIO)
+ * @start:	Start address of iorange
+ * @end:	End address of iorange
+ *
+ * Return: 0 on success, <0 on error
+ */
+int acrn_ioreq_range_add(struct acrn_ioreq_client *client,
+			 u32 type, u64 start, u64 end)
+{
+	struct acrn_ioreq_range *range;
+
+	if (end < start) {
+		dev_err(acrn_dev.this_device,
+			"Invalid IO range [0x%llx,0x%llx]\n", start, end);
+		return -EINVAL;
+	}
+
+	range = kzalloc_obj(*range);
+	if (!range)
+		return -ENOMEM;
+
+	range->type = type;
+	range->start = start;
+	range->end = end;
+
+	write_lock_bh(&client->range_lock);
+	list_add(&range->list, &client->range_list);
+	write_unlock_bh(&client->range_lock);
+
+	return 0;
+}
+
+/**
+ * acrn_ioreq_range_del() - Del an iorange monitored by an ioreq client
+ * @client:	The ioreq client
+ * @type:	Type (ACRN_IOREQ_TYPE_MMIO or ACRN_IOREQ_TYPE_PORTIO)
+ * @start:	Start address of iorange
+ * @end:	End address of iorange
+ */
+void acrn_ioreq_range_del(struct acrn_ioreq_client *client,
+			  u32 type, u64 start, u64 end)
+{
+	struct acrn_ioreq_range *range;
+
+	write_lock_bh(&client->range_lock);
+	list_for_each_entry(range, &client->range_list, list) {
+		if (type == range->type &&
+		    start == range->start &&
+		    end == range->end) {
+			list_del(&range->list);
+			kfree(range);
+			break;
+		}
+	}
+	write_unlock_bh(&client->range_lock);
+}
+
+/*
+ * ioreq_task() is the execution entity of handler thread of an I/O client.
+ * The handler callback of the I/O client is called within the handler thread.
+ */
+static int ioreq_task(void *data)
+{
+	struct acrn_ioreq_client *client = data;
+	struct acrn_io_request *req;
+	unsigned long *ioreqs_map;
+	int vcpu, ret;
+
+	/*
+	 * Lockless access to ioreqs_map is safe, because
+	 * 1) set_bit() and clear_bit() are atomic operations.
+	 * 2) I/O requests arrives serialized. The access flow of ioreqs_map is:
+	 *	set_bit() - in ioreq_work handler
+	 *	Handler callback handles corresponding I/O request
+	 *	clear_bit() - in handler thread (include ACRN userspace)
+	 *	Mark corresponding I/O request completed
+	 *	Loop again if a new I/O request occurs
+	 */
+	ioreqs_map = client->ioreqs_map;
+	while (!kthread_should_stop()) {
+		acrn_ioreq_client_wait(client);
+		while (has_pending_request(client)) {
+			vcpu = find_first_bit(ioreqs_map, client->vm->vcpu_num);
+			req = client->vm->ioreq_buf->req_slot + vcpu;
+			ret = client->handler(client, req);
+			if (ret < 0) {
+				dev_err(acrn_dev.this_device,
+					"IO handle failure: %d\n", ret);
+				break;
+			}
+			acrn_ioreq_complete_request(client, vcpu, req);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * For the non-default I/O clients, give them chance to complete the current
+ * I/O requests if there are any. For the default I/O client, it is safe to
+ * clear all pending I/O requests because the clearing request is from ACRN
+ * userspace.
+ */
+void acrn_ioreq_request_clear(struct acrn_vm *vm)
+{
+	struct acrn_ioreq_client *client;
+	bool has_pending = false;
+	unsigned long vcpu;
+	int retry = 10;
+
+	/*
+	 * IO requests of this VM will be completed directly in
+	 * acrn_ioreq_dispatch if ACRN_VM_FLAG_CLEARING_IOREQ flag is set.
+	 */
+	set_bit(ACRN_VM_FLAG_CLEARING_IOREQ, &vm->flags);
+
+	/*
+	 * acrn_ioreq_request_clear is only called in VM reset case. Simply
+	 * wait 100ms in total for the IO requests' completion.
+	 */
+	do {
+		spin_lock_bh(&vm->ioreq_clients_lock);
+		list_for_each_entry(client, &vm->ioreq_clients, list) {
+			has_pending = has_pending_request(client);
+			if (has_pending)
+				break;
+		}
+		spin_unlock_bh(&vm->ioreq_clients_lock);
+
+		if (has_pending)
+			schedule_timeout_interruptible(HZ / 100);
+	} while (has_pending && --retry > 0);
+	if (retry == 0)
+		dev_warn(acrn_dev.this_device,
+			 "%s cannot flush pending request!\n", client->name);
+
+	/* Clear all ioreqs belonging to the default client */
+	spin_lock_bh(&vm->ioreq_clients_lock);
+	client = vm->default_client;
+	if (client) {
+		for_each_set_bit(vcpu, client->ioreqs_map, ACRN_IO_REQUEST_MAX)
+			acrn_ioreq_complete_request(client, vcpu, NULL);
+	}
+	spin_unlock_bh(&vm->ioreq_clients_lock);
+
+	/* Clear ACRN_VM_FLAG_CLEARING_IOREQ flag after the clearing */
+	clear_bit(ACRN_VM_FLAG_CLEARING_IOREQ, &vm->flags);
+}
+
+int acrn_ioreq_client_wait(struct acrn_ioreq_client *client)
+{
+	if (client->is_default) {
+		/*
+		 * In the default client, a user space thread waits on the
+		 * waitqueue. The is_destroying() check is used to notify user
+		 * space the client is going to be destroyed.
+		 */
+		wait_event_interruptible(client->wq,
+					 has_pending_request(client) ||
+					 is_destroying(client));
+		if (is_destroying(client))
+			return -ENODEV;
+	} else {
+		wait_event_interruptible(client->wq,
+					 has_pending_request(client) ||
+					 kthread_should_stop());
+	}
+
+	return 0;
+}
+
+static bool is_cfg_addr(struct acrn_io_request *req)
+{
+	return ((req->type == ACRN_IOREQ_TYPE_PORTIO) &&
+		(req->reqs.pio_request.address == 0xcf8));
+}
+
+static bool is_cfg_data(struct acrn_io_request *req)
+{
+	return ((req->type == ACRN_IOREQ_TYPE_PORTIO) &&
+		((req->reqs.pio_request.address >= 0xcfc) &&
+		 (req->reqs.pio_request.address < (0xcfc + 4))));
+}
+
+/* The low 8-bit of supported pci_reg addr.*/
+#define PCI_LOWREG_MASK  0xFC
+/* The high 4-bit of supported pci_reg addr */
+#define PCI_HIGHREG_MASK 0xF00
+/* Max number of supported functions */
+#define PCI_FUNCMAX	7
+/* Max number of supported slots */
+#define PCI_SLOTMAX	31
+/* Max number of supported buses */
+#define PCI_BUSMAX	255
+#define CONF1_ENABLE	0x80000000UL
+/*
+ * A PCI configuration space access via PIO 0xCF8 and 0xCFC normally has two
+ * following steps:
+ *   1) writes address into 0xCF8 port
+ *   2) accesses data in/from 0xCFC
+ * This function combines such paired PCI configuration space I/O requests into
+ * one ACRN_IOREQ_TYPE_PCICFG type I/O request and continues the processing.
+ */
+static bool handle_cf8cfc(struct acrn_vm *vm,
+			  struct acrn_io_request *req, u16 vcpu)
+{
+	int offset, pci_cfg_addr, pci_reg;
+	bool is_handled = false;
+
+	if (is_cfg_addr(req)) {
+		WARN_ON(req->reqs.pio_request.size != 4);
+		if (req->reqs.pio_request.direction == ACRN_IOREQ_DIR_WRITE)
+			vm->pci_conf_addr = req->reqs.pio_request.value;
+		else
+			req->reqs.pio_request.value = vm->pci_conf_addr;
+		is_handled = true;
+	} else if (is_cfg_data(req)) {
+		if (!(vm->pci_conf_addr & CONF1_ENABLE)) {
+			if (req->reqs.pio_request.direction ==
+					ACRN_IOREQ_DIR_READ)
+				req->reqs.pio_request.value = 0xffffffff;
+			is_handled = true;
+		} else {
+			offset = req->reqs.pio_request.address - 0xcfc;
+
+			req->type = ACRN_IOREQ_TYPE_PCICFG;
+			pci_cfg_addr = vm->pci_conf_addr;
+			req->reqs.pci_request.bus =
+					(pci_cfg_addr >> 16) & PCI_BUSMAX;
+			req->reqs.pci_request.dev =
+					(pci_cfg_addr >> 11) & PCI_SLOTMAX;
+			req->reqs.pci_request.func =
+					(pci_cfg_addr >> 8) & PCI_FUNCMAX;
+			pci_reg = (pci_cfg_addr & PCI_LOWREG_MASK) +
+				   ((pci_cfg_addr >> 16) & PCI_HIGHREG_MASK);
+			req->reqs.pci_request.reg = pci_reg + offset;
+		}
+	}
+
+	if (is_handled)
+		ioreq_complete_request(vm, vcpu, req);
+
+	return is_handled;
+}
+
+static bool acrn_in_range(struct acrn_ioreq_range *range,
+		     struct acrn_io_request *req)
+{
+	bool ret = false;
+
+	if (range->type == req->type) {
+		switch (req->type) {
+		case ACRN_IOREQ_TYPE_MMIO:
+			if (req->reqs.mmio_request.address >= range->start &&
+			    (req->reqs.mmio_request.address +
+			     req->reqs.mmio_request.size - 1) <= range->end)
+				ret = true;
+			break;
+		case ACRN_IOREQ_TYPE_PORTIO:
+			if (req->reqs.pio_request.address >= range->start &&
+			    (req->reqs.pio_request.address +
+			     req->reqs.pio_request.size - 1) <= range->end)
+				ret = true;
+			break;
+		default:
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static struct acrn_ioreq_client *find_ioreq_client(struct acrn_vm *vm,
+						   struct acrn_io_request *req)
+{
+	struct acrn_ioreq_client *client, *found = NULL;
+	struct acrn_ioreq_range *range;
+
+	lockdep_assert_held(&vm->ioreq_clients_lock);
+
+	list_for_each_entry(client, &vm->ioreq_clients, list) {
+		read_lock_bh(&client->range_lock);
+		list_for_each_entry(range, &client->range_list, list) {
+			if (acrn_in_range(range, req)) {
+				found = client;
+				break;
+			}
+		}
+		read_unlock_bh(&client->range_lock);
+		if (found)
+			break;
+	}
+	return found ? found : vm->default_client;
+}
+
+/**
+ * acrn_ioreq_client_create() - Create an ioreq client
+ * @vm:		The VM that this client belongs to
+ * @handler:	The ioreq_handler of ioreq client acrn_hsm will create a kernel
+ *		thread and call the handler to handle I/O requests.
+ * @priv:	Private data for the handler
+ * @is_default:	If it is the default client
+ * @name:	The name of ioreq client
+ *
+ * Return: acrn_ioreq_client pointer on success, NULL on error
+ */
+struct acrn_ioreq_client *acrn_ioreq_client_create(struct acrn_vm *vm,
+						   ioreq_handler_t handler,
+						   void *priv, bool is_default,
+						   const char *name)
+{
+	struct acrn_ioreq_client *client;
+
+	if (!handler && !is_default) {
+		dev_dbg(acrn_dev.this_device,
+			"Cannot create non-default client w/o handler!\n");
+		return NULL;
+	}
+	client = kzalloc_obj(*client);
+	if (!client)
+		return NULL;
+
+	client->handler = handler;
+	client->vm = vm;
+	client->priv = priv;
+	client->is_default = is_default;
+	if (name)
+		strscpy(client->name, name);
+	rwlock_init(&client->range_lock);
+	INIT_LIST_HEAD(&client->range_list);
+	init_waitqueue_head(&client->wq);
+
+	if (client->handler) {
+		client->thread = kthread_run(ioreq_task, client, "VM%u-%s",
+					     client->vm->vmid, client->name);
+		if (IS_ERR(client->thread)) {
+			kfree(client);
+			return NULL;
+		}
+	}
+
+	spin_lock_bh(&vm->ioreq_clients_lock);
+	if (is_default)
+		vm->default_client = client;
+	else
+		list_add(&client->list, &vm->ioreq_clients);
+	spin_unlock_bh(&vm->ioreq_clients_lock);
+
+	dev_dbg(acrn_dev.this_device, "Created ioreq client %s.\n", name);
+	return client;
+}
+
+/**
+ * acrn_ioreq_client_destroy() - Destroy an ioreq client
+ * @client:	The ioreq client
+ */
+void acrn_ioreq_client_destroy(struct acrn_ioreq_client *client)
+{
+	struct acrn_ioreq_range *range, *next;
+	struct acrn_vm *vm = client->vm;
+
+	dev_dbg(acrn_dev.this_device,
+		"Destroy ioreq client %s.\n", client->name);
+	ioreq_pause();
+	set_bit(ACRN_IOREQ_CLIENT_DESTROYING, &client->flags);
+	if (client->is_default)
+		wake_up_interruptible(&client->wq);
+	else
+		kthread_stop(client->thread);
+
+	spin_lock_bh(&vm->ioreq_clients_lock);
+	if (client->is_default)
+		vm->default_client = NULL;
+	else
+		list_del(&client->list);
+	spin_unlock_bh(&vm->ioreq_clients_lock);
+
+	write_lock_bh(&client->range_lock);
+	list_for_each_entry_safe(range, next, &client->range_list, list) {
+		list_del(&range->list);
+		kfree(range);
+	}
+	write_unlock_bh(&client->range_lock);
+	kfree(client);
+
+	ioreq_resume();
+}
+
+static int acrn_ioreq_dispatch(struct acrn_vm *vm)
+{
+	struct acrn_ioreq_client *client;
+	struct acrn_io_request *req;
+	int i;
+
+	for (i = 0; i < vm->vcpu_num; i++) {
+		req = vm->ioreq_buf->req_slot + i;
+
+		/* barrier the read of processed of acrn_io_request */
+		if (smp_load_acquire(&req->processed) ==
+				     ACRN_IOREQ_STATE_PENDING) {
+			/* Complete the IO request directly in clearing stage */
+			if (test_bit(ACRN_VM_FLAG_CLEARING_IOREQ, &vm->flags)) {
+				ioreq_complete_request(vm, i, req);
+				continue;
+			}
+			if (handle_cf8cfc(vm, req, i))
+				continue;
+
+			spin_lock_bh(&vm->ioreq_clients_lock);
+			client = find_ioreq_client(vm, req);
+			if (!client) {
+				dev_err(acrn_dev.this_device,
+					"Failed to find ioreq client!\n");
+				spin_unlock_bh(&vm->ioreq_clients_lock);
+				return -EINVAL;
+			}
+			if (!client->is_default)
+				req->kernel_handled = 1;
+			else
+				req->kernel_handled = 0;
+			/*
+			 * Add barrier() to make sure the writes are done
+			 * before setting ACRN_IOREQ_STATE_PROCESSING
+			 */
+			smp_store_release(&req->processed,
+					  ACRN_IOREQ_STATE_PROCESSING);
+			set_bit(i, client->ioreqs_map);
+			wake_up_interruptible(&client->wq);
+			spin_unlock_bh(&vm->ioreq_clients_lock);
+		}
+	}
+
+	return 0;
+}
+
+static void ioreq_dispatcher(struct work_struct *work)
+{
+	struct acrn_vm *vm;
+
+	read_lock(&acrn_vm_list_lock);
+	list_for_each_entry(vm, &acrn_vm_list, list) {
+		if (!vm->ioreq_buf)
+			break;
+		acrn_ioreq_dispatch(vm);
+	}
+	read_unlock(&acrn_vm_list_lock);
+}
+
+static void ioreq_intr_handler(void)
+{
+	queue_work(ioreq_wq, &ioreq_work);
+}
+
+static void ioreq_pause(void)
+{
+	/* Flush and unarm the handler to ensure no I/O requests pending */
+	acrn_remove_intr_handler();
+	drain_workqueue(ioreq_wq);
+}
+
+static void ioreq_resume(void)
+{
+	/* Schedule after enabling in case other clients miss interrupt */
+	acrn_setup_intr_handler(ioreq_intr_handler);
+	queue_work(ioreq_wq, &ioreq_work);
+}
+
+int acrn_ioreq_intr_setup(void)
+{
+	acrn_setup_intr_handler(ioreq_intr_handler);
+	ioreq_wq = alloc_ordered_workqueue("ioreq_wq",
+					   WQ_HIGHPRI | WQ_MEM_RECLAIM);
+	if (!ioreq_wq) {
+		dev_err(acrn_dev.this_device, "Failed to alloc workqueue!\n");
+		acrn_remove_intr_handler();
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+void acrn_ioreq_intr_remove(void)
+{
+	if (ioreq_wq)
+		destroy_workqueue(ioreq_wq);
+	acrn_remove_intr_handler();
+}
+
+int acrn_ioreq_init(struct acrn_vm *vm, u64 buf_vma)
+{
+	struct acrn_ioreq_buffer *set_buffer;
+	struct page *page;
+	int ret;
+
+	if (vm->ioreq_buf)
+		return -EEXIST;
+
+	set_buffer = kzalloc_obj(*set_buffer);
+	if (!set_buffer)
+		return -ENOMEM;
+
+	ret = pin_user_pages_fast(buf_vma, 1,
+				  FOLL_WRITE | FOLL_LONGTERM, &page);
+	if (unlikely(ret != 1) || !page) {
+		dev_err(acrn_dev.this_device, "Failed to pin ioreq page!\n");
+		ret = -EFAULT;
+		goto free_buf;
+	}
+
+	vm->ioreq_buf = page_address(page);
+	vm->ioreq_page = page;
+	set_buffer->ioreq_buf = page_to_phys(page);
+	ret = hcall_set_ioreq_buffer(vm->vmid, virt_to_phys(set_buffer));
+	if (ret < 0) {
+		dev_err(acrn_dev.this_device, "Failed to init ioreq buffer!\n");
+		unpin_user_page(page);
+		vm->ioreq_buf = NULL;
+		goto free_buf;
+	}
+
+	dev_dbg(acrn_dev.this_device,
+		"Init ioreq buffer %p!\n", vm->ioreq_buf);
+	ret = 0;
+free_buf:
+	kfree(set_buffer);
+	return ret;
+}
+
+void acrn_ioreq_deinit(struct acrn_vm *vm)
+{
+	struct acrn_ioreq_client *client, *next;
+
+	dev_dbg(acrn_dev.this_device,
+		"Deinit ioreq buffer %p!\n", vm->ioreq_buf);
+	/* Destroy all clients belonging to this VM */
+	list_for_each_entry_safe(client, next, &vm->ioreq_clients, list)
+		acrn_ioreq_client_destroy(client);
+	if (vm->default_client)
+		acrn_ioreq_client_destroy(vm->default_client);
+
+	if (vm->ioreq_buf && vm->ioreq_page) {
+		unpin_user_page(vm->ioreq_page);
+		vm->ioreq_buf = NULL;
+	}
+}

linux-7.2.3/drivers/virt/acrn/irqfd.c

@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACRN HSM irqfd: use eventfd objects to inject virtual interrupts
+ *
+ * Copyright (C) 2020 Intel Corporation. All rights reserved.
+ *
+ * Authors:
+ *	Shuo Liu <shuo.a.liu@intel.com>
+ *	Yakui Zhao <yakui.zhao@intel.com>
+ */
+
+#include <linux/eventfd.h>
+#include <linux/file.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+
+#include "acrn_drv.h"
+
+/* Cleanup work has been queued; set via test_and_set_bit(). */
+#define HSM_IRQFD_FLAG_SHUTDOWN	0
+
+/**
+ * struct hsm_irqfd - Properties of HSM irqfd
+ * @vm:		Associated VM pointer
+ * @wait:	Entry of wait-queue
+ * @shutdown:	Async shutdown work
+ * @eventfd:	Associated eventfd
+ * @list:	Entry within &acrn_vm.irqfds of irqfds of a VM
+ * @pt:		Structure for select/poll on the associated eventfd
+ * @msi:	MSI data
+ * @flags:	Internal lifecycle flags (HSM_IRQFD_FLAG_*)
+ */
+struct hsm_irqfd {
+	struct acrn_vm		*vm;
+	wait_queue_entry_t	wait;
+	struct work_struct	shutdown;
+	struct eventfd_ctx	*eventfd;
+	struct list_head	list;
+	poll_table		pt;
+	struct acrn_msi_entry	msi;
+	unsigned long		flags;
+};
+
+static void acrn_irqfd_inject(struct hsm_irqfd *irqfd)
+{
+	struct acrn_vm *vm = irqfd->vm;
+
+	acrn_msi_inject(vm, irqfd->msi.msi_addr,
+			irqfd->msi.msi_data);
+}
+
+/* Queue the cleanup work at most once. Safe from atomic context. */
+static void hsm_irqfd_queue_shutdown(struct hsm_irqfd *irqfd)
+{
+	if (!test_and_set_bit(HSM_IRQFD_FLAG_SHUTDOWN, &irqfd->flags))
+		queue_work(irqfd->vm->irqfd_wq, &irqfd->shutdown);
+}
+
+/* Sole owner of @irqfd: unhook waitqueue, drop eventfd ref, free. */
+static void hsm_irqfd_shutdown_work(struct work_struct *work)
+{
+	struct hsm_irqfd *irqfd = container_of(work, struct hsm_irqfd,
+					       shutdown);
+	struct acrn_vm *vm = irqfd->vm;
+	u64 cnt;
+
+	mutex_lock(&vm->irqfds_lock);
+	if (!list_empty(&irqfd->list))
+		list_del_init(&irqfd->list);
+	mutex_unlock(&vm->irqfds_lock);
+
+	eventfd_ctx_remove_wait_queue(irqfd->eventfd, &irqfd->wait, &cnt);
+	eventfd_ctx_put(irqfd->eventfd);
+	kfree(irqfd);
+}
+
+/* Called with wqh->lock held and interrupts disabled */
+static int hsm_irqfd_wakeup(wait_queue_entry_t *wait, unsigned int mode,
+			    int sync, void *key)
+{
+	unsigned long poll_bits = (unsigned long)key;
+	struct hsm_irqfd *irqfd;
+
+	irqfd = container_of(wait, struct hsm_irqfd, wait);
+
+	if (poll_bits & POLLIN)
+		/* An event has been signaled, inject an interrupt */
+		acrn_irqfd_inject(irqfd);
+
+	if (poll_bits & POLLHUP)
+		/* Defer teardown to the cleanup work; can't sleep here. */
+		hsm_irqfd_queue_shutdown(irqfd);
+
+	return 0;
+}
+
+static void hsm_irqfd_poll_func(struct file *file, wait_queue_head_t *wqh,
+				poll_table *pt)
+{
+	struct hsm_irqfd *irqfd;
+
+	irqfd = container_of(pt, struct hsm_irqfd, pt);
+	add_wait_queue(wqh, &irqfd->wait);
+}
+
+/*
+ * Assign an eventfd to a VM and create a HSM irqfd associated with the
+ * eventfd. The properties of the HSM irqfd are built from a &struct
+ * acrn_irqfd.
+ */
+static int acrn_irqfd_assign(struct acrn_vm *vm, struct acrn_irqfd *args)
+{
+	struct eventfd_ctx *eventfd = NULL;
+	struct hsm_irqfd *irqfd, *tmp;
+	__poll_t events;
+	int ret = 0;
+
+	irqfd = kzalloc_obj(*irqfd);
+	if (!irqfd)
+		return -ENOMEM;
+
+	irqfd->vm = vm;
+	memcpy(&irqfd->msi, &args->msi, sizeof(args->msi));
+	INIT_LIST_HEAD(&irqfd->list);
+	INIT_WORK(&irqfd->shutdown, hsm_irqfd_shutdown_work);
+
+	CLASS(fd, f)(args->fd);
+	if (fd_empty(f)) {
+		ret = -EBADF;
+		goto out;
+	}
+
+	eventfd = eventfd_ctx_fileget(fd_file(f));
+	if (IS_ERR(eventfd)) {
+		ret = PTR_ERR(eventfd);
+		goto out;
+	}
+
+	irqfd->eventfd = eventfd;
+
+	/*
+	 * Install custom wake-up handling to be notified whenever underlying
+	 * eventfd is signaled.
+	 */
+	init_waitqueue_func_entry(&irqfd->wait, hsm_irqfd_wakeup);
+	init_poll_funcptr(&irqfd->pt, hsm_irqfd_poll_func);
+
+	/*
+	 * Hold irqfds_lock across waitqueue install and list_add so the
+	 * irqfd is not visible to deassign/deinit before its waitqueue
+	 * entry is in place, and any racing EPOLLHUP cleanup work blocks
+	 * on irqfds_lock until publication completes.
+	 */
+	mutex_lock(&vm->irqfds_lock);
+	list_for_each_entry(tmp, &vm->irqfds, list) {
+		if (irqfd->eventfd != tmp->eventfd)
+			continue;
+		ret = -EBUSY;
+		mutex_unlock(&vm->irqfds_lock);
+		goto fail;
+	}
+
+	events = vfs_poll(fd_file(f), &irqfd->pt);
+	list_add_tail(&irqfd->list, &vm->irqfds);
+	if (events & EPOLLIN)
+		acrn_irqfd_inject(irqfd);
+	mutex_unlock(&vm->irqfds_lock);
+
+	return 0;
+fail:
+	eventfd_ctx_put(eventfd);
+out:
+	kfree(irqfd);
+	return ret;
+}
+
+static int acrn_irqfd_deassign(struct acrn_vm *vm,
+			       struct acrn_irqfd *args)
+{
+	struct hsm_irqfd *irqfd, *tmp;
+	struct eventfd_ctx *eventfd;
+
+	eventfd = eventfd_ctx_fdget(args->fd);
+	if (IS_ERR(eventfd))
+		return PTR_ERR(eventfd);
+
+	mutex_lock(&vm->irqfds_lock);
+	list_for_each_entry_safe(irqfd, tmp, &vm->irqfds, list) {
+		if (irqfd->eventfd == eventfd) {
+			list_del_init(&irqfd->list);
+			hsm_irqfd_queue_shutdown(irqfd);
+			break;
+		}
+	}
+	mutex_unlock(&vm->irqfds_lock);
+	eventfd_ctx_put(eventfd);
+
+	/* Wait for cleanup work to finish so the eventfd is fully detached. */
+	flush_workqueue(vm->irqfd_wq);
+
+	return 0;
+}
+
+int acrn_irqfd_config(struct acrn_vm *vm, struct acrn_irqfd *args)
+{
+	int ret;
+
+	if (args->flags & ACRN_IRQFD_FLAG_DEASSIGN)
+		ret = acrn_irqfd_deassign(vm, args);
+	else
+		ret = acrn_irqfd_assign(vm, args);
+
+	return ret;
+}
+
+int acrn_irqfd_init(struct acrn_vm *vm)
+{
+	INIT_LIST_HEAD(&vm->irqfds);
+	mutex_init(&vm->irqfds_lock);
+	vm->irqfd_wq = alloc_workqueue("acrn_irqfd-%u", WQ_PERCPU, 0, vm->vmid);
+	if (!vm->irqfd_wq)
+		return -ENOMEM;
+
+	dev_dbg(acrn_dev.this_device, "VM %u irqfd init.\n", vm->vmid);
+	return 0;
+}
+
+void acrn_irqfd_deinit(struct acrn_vm *vm)
+{
+	struct hsm_irqfd *irqfd, *next;
+
+	dev_dbg(acrn_dev.this_device, "VM %u irqfd deinit.\n", vm->vmid);
+
+	mutex_lock(&vm->irqfds_lock);
+	list_for_each_entry_safe(irqfd, next, &vm->irqfds, list) {
+		list_del_init(&irqfd->list);
+		hsm_irqfd_queue_shutdown(irqfd);
+	}
+	mutex_unlock(&vm->irqfds_lock);
+
+	/* Drain all cleanup work before tearing the workqueue down. */
+	flush_workqueue(vm->irqfd_wq);
+	destroy_workqueue(vm->irqfd_wq);
+}

linux-7.2.3/drivers/virt/acrn/mm.c

@@ -0,0 +1,367 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACRN: Memory mapping management
+ *
+ * Copyright (C) 2020 Intel Corporation. All rights reserved.
+ *
+ * Authors:
+ *	Fei Li <lei1.li@intel.com>
+ *	Shuo Liu <shuo.a.liu@intel.com>
+ */
+
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+#include "acrn_drv.h"
+
+static int modify_region(struct acrn_vm *vm, struct vm_memory_region_op *region)
+{
+	struct vm_memory_region_batch *regions;
+	int ret;
+
+	regions = kzalloc_obj(*regions);
+	if (!regions)
+		return -ENOMEM;
+
+	regions->vmid = vm->vmid;
+	regions->regions_num = 1;
+	regions->regions_gpa = virt_to_phys(region);
+
+	ret = hcall_set_memory_regions(virt_to_phys(regions));
+	if (ret < 0)
+		dev_dbg(acrn_dev.this_device,
+			"Failed to set memory region for VM[%u]!\n", vm->vmid);
+
+	kfree(regions);
+	return ret;
+}
+
+/**
+ * acrn_mm_region_add() - Set up the EPT mapping of a memory region.
+ * @vm:			User VM.
+ * @user_gpa:		A GPA of User VM.
+ * @service_gpa:	A GPA of Service VM.
+ * @size:		Size of the region.
+ * @mem_type:		Combination of ACRN_MEM_TYPE_*.
+ * @mem_access_right:	Combination of ACRN_MEM_ACCESS_*.
+ *
+ * Return: 0 on success, <0 on error.
+ */
+int acrn_mm_region_add(struct acrn_vm *vm, u64 user_gpa, u64 service_gpa,
+		       u64 size, u32 mem_type, u32 mem_access_right)
+{
+	struct vm_memory_region_op *region;
+	int ret = 0;
+
+	region = kzalloc_obj(*region);
+	if (!region)
+		return -ENOMEM;
+
+	region->type = ACRN_MEM_REGION_ADD;
+	region->user_vm_pa = user_gpa;
+	region->service_vm_pa = service_gpa;
+	region->size = size;
+	region->attr = ((mem_type & ACRN_MEM_TYPE_MASK) |
+			(mem_access_right & ACRN_MEM_ACCESS_RIGHT_MASK));
+	ret = modify_region(vm, region);
+
+	dev_dbg(acrn_dev.this_device,
+		"%s: user-GPA[%p] service-GPA[%p] size[0x%llx].\n",
+		__func__, (void *)user_gpa, (void *)service_gpa, size);
+	kfree(region);
+	return ret;
+}
+
+/**
+ * acrn_mm_region_del() - Del the EPT mapping of a memory region.
+ * @vm:		User VM.
+ * @user_gpa:	A GPA of the User VM.
+ * @size:	Size of the region.
+ *
+ * Return: 0 on success, <0 for error.
+ */
+int acrn_mm_region_del(struct acrn_vm *vm, u64 user_gpa, u64 size)
+{
+	struct vm_memory_region_op *region;
+	int ret = 0;
+
+	region = kzalloc_obj(*region);
+	if (!region)
+		return -ENOMEM;
+
+	region->type = ACRN_MEM_REGION_DEL;
+	region->user_vm_pa = user_gpa;
+	region->service_vm_pa = 0UL;
+	region->size = size;
+	region->attr = 0U;
+
+	ret = modify_region(vm, region);
+
+	dev_dbg(acrn_dev.this_device, "%s: user-GPA[%p] size[0x%llx].\n",
+		__func__, (void *)user_gpa, size);
+	kfree(region);
+	return ret;
+}
+
+int acrn_vm_memseg_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap)
+{
+	int ret;
+
+	if (memmap->type == ACRN_MEMMAP_RAM)
+		return acrn_vm_ram_map(vm, memmap);
+
+	if (memmap->type != ACRN_MEMMAP_MMIO) {
+		dev_dbg(acrn_dev.this_device,
+			"Invalid memmap type: %u\n", memmap->type);
+		return -EINVAL;
+	}
+
+	ret = acrn_mm_region_add(vm, memmap->user_vm_pa,
+				 memmap->service_vm_pa, memmap->len,
+				 ACRN_MEM_TYPE_UC, memmap->attr);
+	if (ret < 0)
+		dev_dbg(acrn_dev.this_device,
+			"Add memory region failed, VM[%u]!\n", vm->vmid);
+
+	return ret;
+}
+
+int acrn_vm_memseg_unmap(struct acrn_vm *vm, struct acrn_vm_memmap *memmap)
+{
+	int ret;
+
+	if (memmap->type != ACRN_MEMMAP_MMIO) {
+		dev_dbg(acrn_dev.this_device,
+			"Invalid memmap type: %u\n", memmap->type);
+		return -EINVAL;
+	}
+
+	ret = acrn_mm_region_del(vm, memmap->user_vm_pa, memmap->len);
+	if (ret < 0)
+		dev_dbg(acrn_dev.this_device,
+			"Del memory region failed, VM[%u]!\n", vm->vmid);
+
+	return ret;
+}
+
+/**
+ * acrn_vm_ram_map() - Create a RAM EPT mapping of User VM.
+ * @vm:		The User VM pointer
+ * @memmap:	Info of the EPT mapping
+ *
+ * Return: 0 on success, <0 for error.
+ */
+int acrn_vm_ram_map(struct acrn_vm *vm, struct acrn_vm_memmap *memmap)
+{
+	struct vm_memory_region_batch *regions_info;
+	int nr_pages, i, order, nr_regions = 0;
+	struct vm_memory_mapping *region_mapping;
+	struct vm_memory_region_op *vm_region;
+	struct page **pages = NULL, *page;
+	void *remap_vaddr;
+	int ret, pinned;
+	u64 user_vm_pa;
+	struct vm_area_struct *vma;
+
+	if (!vm || !memmap)
+		return -EINVAL;
+
+	/* Get the page number of the map region */
+	nr_pages = memmap->len >> PAGE_SHIFT;
+	if (!nr_pages)
+		return -EINVAL;
+
+	mmap_read_lock(current->mm);
+	vma = vma_lookup(current->mm, memmap->vma_base);
+	if (vma && ((vma->vm_flags & VM_PFNMAP) != 0)) {
+		unsigned long start_pfn, cur_pfn;
+		bool writable;
+
+		if ((memmap->vma_base + memmap->len) > vma->vm_end) {
+			mmap_read_unlock(current->mm);
+			return -EINVAL;
+		}
+
+		for (i = 0; i < nr_pages; i++) {
+			struct follow_pfnmap_args args = {
+				.vma = vma,
+				.address = memmap->vma_base + i * PAGE_SIZE,
+			};
+
+			ret = follow_pfnmap_start(&args);
+			if (ret)
+				break;
+
+			cur_pfn = args.pfn;
+			if (i == 0)
+				start_pfn = cur_pfn;
+			writable = args.writable;
+			follow_pfnmap_end(&args);
+
+			/* Disallow write access if the PTE is not writable. */
+			if (!writable &&
+			    (memmap->attr & ACRN_MEM_ACCESS_WRITE)) {
+				ret = -EFAULT;
+				break;
+			}
+
+			/* Disallow refcounted pages. */
+			if (pfn_valid(cur_pfn) &&
+			    !PageReserved(pfn_to_page(cur_pfn))) {
+				ret = -EFAULT;
+				break;
+			}
+
+			/* Disallow non-contiguous ranges. */
+			if (cur_pfn != start_pfn + i) {
+				ret = -EINVAL;
+				break;
+			}
+		}
+		mmap_read_unlock(current->mm);
+
+		if (ret) {
+			dev_dbg(acrn_dev.this_device,
+				"Failed to lookup PFN at VMA:%p.\n", (void *)memmap->vma_base);
+			return ret;
+		}
+
+		return acrn_mm_region_add(vm, memmap->user_vm_pa,
+			 PFN_PHYS(start_pfn), memmap->len,
+			 ACRN_MEM_TYPE_WB, memmap->attr);
+	}
+	mmap_read_unlock(current->mm);
+
+	pages = vzalloc(array_size(nr_pages, sizeof(*pages)));
+	if (!pages)
+		return -ENOMEM;
+
+	/* Lock the pages of user memory map region */
+	pinned = pin_user_pages_fast(memmap->vma_base,
+				     nr_pages, FOLL_WRITE | FOLL_LONGTERM,
+				     pages);
+	if (pinned < 0) {
+		ret = pinned;
+		goto free_pages;
+	} else if (pinned != nr_pages) {
+		ret = -EFAULT;
+		goto put_pages;
+	}
+
+	/* Create a kernel map for the map region */
+	remap_vaddr = vmap(pages, nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!remap_vaddr) {
+		ret = -ENOMEM;
+		goto put_pages;
+	}
+
+	/* Record Service VM va <-> User VM pa mapping */
+	mutex_lock(&vm->regions_mapping_lock);
+	region_mapping = &vm->regions_mapping[vm->regions_mapping_count];
+	if (vm->regions_mapping_count < ACRN_MEM_MAPPING_MAX) {
+		region_mapping->pages = pages;
+		region_mapping->npages = nr_pages;
+		region_mapping->size = memmap->len;
+		region_mapping->service_vm_va = remap_vaddr;
+		region_mapping->user_vm_pa = memmap->user_vm_pa;
+		vm->regions_mapping_count++;
+	} else {
+		dev_warn(acrn_dev.this_device,
+			"Run out of memory mapping slots!\n");
+		ret = -ENOMEM;
+		mutex_unlock(&vm->regions_mapping_lock);
+		goto unmap_no_count;
+	}
+	mutex_unlock(&vm->regions_mapping_lock);
+
+	/* Calculate count of vm_memory_region_op */
+	for (i = 0; i < nr_pages; i += 1 << order) {
+		page = pages[i];
+		VM_BUG_ON_PAGE(PageTail(page), page);
+		order = compound_order(page);
+		nr_regions++;
+	}
+
+	/* Prepare the vm_memory_region_batch */
+	regions_info = kzalloc_flex(*regions_info, regions_op, nr_regions);
+	if (!regions_info) {
+		ret = -ENOMEM;
+		goto unmap_kernel_map;
+	}
+	regions_info->regions_num = nr_regions;
+
+	/* Fill each vm_memory_region_op */
+	vm_region = regions_info->regions_op;
+	regions_info->vmid = vm->vmid;
+	regions_info->regions_gpa = virt_to_phys(vm_region);
+	user_vm_pa = memmap->user_vm_pa;
+	for (i = 0; i < nr_pages; i += 1 << order) {
+		u32 region_size;
+
+		page = pages[i];
+		VM_BUG_ON_PAGE(PageTail(page), page);
+		order = compound_order(page);
+		region_size = PAGE_SIZE << order;
+		vm_region->type = ACRN_MEM_REGION_ADD;
+		vm_region->user_vm_pa = user_vm_pa;
+		vm_region->service_vm_pa = page_to_phys(page);
+		vm_region->size = region_size;
+		vm_region->attr = (ACRN_MEM_TYPE_WB & ACRN_MEM_TYPE_MASK) |
+				  (memmap->attr & ACRN_MEM_ACCESS_RIGHT_MASK);
+
+		vm_region++;
+		user_vm_pa += region_size;
+	}
+
+	/* Inform the ACRN Hypervisor to set up EPT mappings */
+	ret = hcall_set_memory_regions(virt_to_phys(regions_info));
+	if (ret < 0) {
+		dev_dbg(acrn_dev.this_device,
+			"Failed to set regions, VM[%u]!\n", vm->vmid);
+		goto unset_region;
+	}
+	kfree(regions_info);
+
+	dev_dbg(acrn_dev.this_device,
+		"%s: VM[%u] service-GVA[%p] user-GPA[%p] size[0x%llx]\n",
+		__func__, vm->vmid,
+		remap_vaddr, (void *)memmap->user_vm_pa, memmap->len);
+	return ret;
+
+unset_region:
+	kfree(regions_info);
+unmap_kernel_map:
+	mutex_lock(&vm->regions_mapping_lock);
+	vm->regions_mapping_count--;
+	mutex_unlock(&vm->regions_mapping_lock);
+unmap_no_count:
+	vunmap(remap_vaddr);
+put_pages:
+	for (i = 0; i < pinned; i++)
+		unpin_user_page(pages[i]);
+free_pages:
+	vfree(pages);
+	return ret;
+}
+
+/**
+ * acrn_vm_all_ram_unmap() - Destroy a RAM EPT mapping of User VM.
+ * @vm:	The User VM
+ */
+void acrn_vm_all_ram_unmap(struct acrn_vm *vm)
+{
+	struct vm_memory_mapping *region_mapping;
+	int i, j;
+
+	mutex_lock(&vm->regions_mapping_lock);
+	for (i = 0; i < vm->regions_mapping_count; i++) {
+		region_mapping = &vm->regions_mapping[i];
+		vunmap(region_mapping->service_vm_va);
+		for (j = 0; j < region_mapping->npages; j++)
+			unpin_user_page(region_mapping->pages[j]);
+		vfree(region_mapping->pages);
+	}
+	mutex_unlock(&vm->regions_mapping_lock);
+}

linux-7.2.3/drivers/virt/acrn/vm.c

@@ -0,0 +1,126 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ACRN_HSM: Virtual Machine management
+ *
+ * Copyright (C) 2020 Intel Corporation. All rights reserved.
+ *
+ * Authors:
+ *	Jason Chen CJ <jason.cj.chen@intel.com>
+ *	Yakui Zhao <yakui.zhao@intel.com>
+ */
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/slab.h>
+
+#include "acrn_drv.h"
+
+/* List of VMs */
+LIST_HEAD(acrn_vm_list);
+/*
+ * acrn_vm_list is read in a worker thread which dispatch I/O requests and
+ * is wrote in VM creation ioctl. Use the rwlock mechanism to protect it.
+ */
+DEFINE_RWLOCK(acrn_vm_list_lock);
+
+struct acrn_vm *acrn_vm_create(struct acrn_vm *vm,
+			       struct acrn_vm_creation *vm_param)
+{
+	int ret;
+
+	ret = hcall_create_vm(virt_to_phys(vm_param));
+	if (ret < 0 || vm_param->vmid == ACRN_INVALID_VMID) {
+		dev_err(acrn_dev.this_device,
+			"Failed to create VM! Error: %d\n", ret);
+		return NULL;
+	}
+
+	mutex_init(&vm->regions_mapping_lock);
+	INIT_LIST_HEAD(&vm->ioreq_clients);
+	spin_lock_init(&vm->ioreq_clients_lock);
+	vm->vmid = vm_param->vmid;
+	vm->vcpu_num = vm_param->vcpu_num;
+
+	if (acrn_ioreq_init(vm, vm_param->ioreq_buf) < 0) {
+		hcall_destroy_vm(vm_param->vmid);
+		vm->vmid = ACRN_INVALID_VMID;
+		return NULL;
+	}
+
+	write_lock_bh(&acrn_vm_list_lock);
+	list_add(&vm->list, &acrn_vm_list);
+	write_unlock_bh(&acrn_vm_list_lock);
+
+	acrn_ioeventfd_init(vm);
+	acrn_irqfd_init(vm);
+	dev_dbg(acrn_dev.this_device, "VM %u created.\n", vm->vmid);
+	return vm;
+}
+
+int acrn_vm_destroy(struct acrn_vm *vm)
+{
+	int ret;
+
+	if (vm->vmid == ACRN_INVALID_VMID ||
+	    test_and_set_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags))
+		return 0;
+
+	ret = hcall_destroy_vm(vm->vmid);
+	if (ret < 0) {
+		dev_err(acrn_dev.this_device,
+			"Failed to destroy VM %u\n", vm->vmid);
+		clear_bit(ACRN_VM_FLAG_DESTROYED, &vm->flags);
+		return ret;
+	}
+
+	/* Remove from global VM list */
+	write_lock_bh(&acrn_vm_list_lock);
+	list_del_init(&vm->list);
+	write_unlock_bh(&acrn_vm_list_lock);
+
+	acrn_ioeventfd_deinit(vm);
+	acrn_irqfd_deinit(vm);
+	acrn_ioreq_deinit(vm);
+
+	if (vm->monitor_page) {
+		put_page(vm->monitor_page);
+		vm->monitor_page = NULL;
+	}
+
+	acrn_vm_all_ram_unmap(vm);
+
+	dev_dbg(acrn_dev.this_device, "VM %u destroyed.\n", vm->vmid);
+	vm->vmid = ACRN_INVALID_VMID;
+	return 0;
+}
+
+/**
+ * acrn_msi_inject() - Inject a MSI interrupt into a User VM
+ * @vm:		User VM
+ * @msi_addr:	The MSI address
+ * @msi_data:	The MSI data
+ *
+ * Return: 0 on success, <0 on error
+ */
+int acrn_msi_inject(struct acrn_vm *vm, u64 msi_addr, u64 msi_data)
+{
+	struct acrn_msi_entry *msi;
+	int ret;
+
+	/* might be used in interrupt context, so use GFP_ATOMIC */
+	msi = kzalloc_obj(*msi, GFP_ATOMIC);
+	if (!msi)
+		return -ENOMEM;
+
+	/*
+	 * msi_addr: addr[19:12] with dest vcpu id
+	 * msi_data: data[7:0] with vector
+	 */
+	msi->msi_addr = msi_addr;
+	msi->msi_data = msi_data;
+	ret = hcall_inject_msi(vm->vmid, virt_to_phys(msi));
+	if (ret < 0)
+		dev_err(acrn_dev.this_device,
+			"Failed to inject MSI to VM %u!\n", vm->vmid);
+	kfree(msi);
+	return ret;
+}

linux-7.2.3/drivers/virt/coco/Kconfig

@@ -0,0 +1,23 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Confidential computing related collateral
+#
+
+if VIRT_DRIVERS
+source "drivers/virt/coco/efi_secret/Kconfig"
+
+source "drivers/virt/coco/pkvm-guest/Kconfig"
+
+source "drivers/virt/coco/sev-guest/Kconfig"
+
+source "drivers/virt/coco/tdx-guest/Kconfig"
+
+source "drivers/virt/coco/arm-cca-guest/Kconfig"
+
+source "drivers/virt/coco/guest/Kconfig"
+endif
+
+source "drivers/virt/coco/tdx-host/Kconfig"
+
+config TSM
+	bool

linux-7.2.3/drivers/virt/coco/Makefile

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Confidential computing related collateral
+#
+obj-$(CONFIG_EFI_SECRET)	+= efi_secret/
+obj-$(CONFIG_ARM_PKVM_GUEST)	+= pkvm-guest/
+obj-$(CONFIG_SEV_GUEST)		+= sev-guest/
+obj-$(CONFIG_INTEL_TDX_GUEST)	+= tdx-guest/
+obj-$(CONFIG_INTEL_TDX_HOST)	+= tdx-host/
+obj-$(CONFIG_ARM_CCA_GUEST)	+= arm-cca-guest/
+obj-$(CONFIG_TSM) 		+= tsm-core.o
+obj-$(CONFIG_TSM_GUEST)		+= guest/

linux-7.2.3/drivers/virt/coco/arm-cca-guest/Kconfig

@@ -0,0 +1,10 @@
+config ARM_CCA_GUEST
+	tristate "Arm CCA Guest driver"
+	depends on ARM64
+	select TSM_REPORTS
+	help
+	  The driver provides userspace interface to request and
+	  attestation report from the Realm Management Monitor(RMM).
+
+	  If you choose 'M' here, this module will be called
+	  arm-cca-guest.

linux-7.2.3/drivers/virt/coco/arm-cca-guest/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_ARM_CCA_GUEST) += arm-cca-guest.o

linux-7.2.3/drivers/virt/coco/arm-cca-guest/arm-cca-guest.c

@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2023 ARM Ltd.
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/cc_platform.h>
+#include <linux/kernel.h>
+#include <linux/device-id/platform.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/tsm.h>
+#include <linux/types.h>
+
+#include <asm/rsi.h>
+
+/**
+ * struct arm_cca_token_info - a descriptor for the token buffer.
+ * @challenge:		Pointer to the challenge data
+ * @challenge_size:	Size of the challenge data
+ * @granule:		PA of the granule to which the token will be written
+ * @offset:		Offset within granule to start of buffer in bytes
+ * @result:		result of rsi_attestation_token_continue operation
+ */
+struct arm_cca_token_info {
+	void           *challenge;
+	unsigned long   challenge_size;
+	phys_addr_t     granule;
+	unsigned long   offset;
+	unsigned long   result;
+};
+
+static void arm_cca_attestation_init(void *param)
+{
+	struct arm_cca_token_info *info;
+
+	info = (struct arm_cca_token_info *)param;
+
+	info->result = rsi_attestation_token_init(info->challenge,
+						  info->challenge_size);
+}
+
+/**
+ * arm_cca_attestation_continue - Retrieve the attestation token data.
+ *
+ * @param: pointer to the arm_cca_token_info
+ *
+ * Attestation token generation is a long running operation and therefore
+ * the token data may not be retrieved in a single call. Moreover, the
+ * token retrieval operation must be requested on the same CPU on which the
+ * attestation token generation was initialised.
+ * This helper function is therefore scheduled on the same CPU multiple
+ * times until the entire token data is retrieved.
+ */
+static void arm_cca_attestation_continue(void *param)
+{
+	unsigned long len;
+	unsigned long size;
+	struct arm_cca_token_info *info;
+
+	info = (struct arm_cca_token_info *)param;
+
+	size = RSI_GRANULE_SIZE - info->offset;
+	info->result = rsi_attestation_token_continue(info->granule,
+						      info->offset, size, &len);
+	info->offset += len;
+}
+
+/**
+ * arm_cca_report_new - Generate a new attestation token.
+ *
+ * @report: pointer to the TSM report context information.
+ * @data:  pointer to the context specific data for this module.
+ *
+ * Initialise the attestation token generation using the challenge data
+ * passed in the TSM descriptor. Allocate memory for the attestation token
+ * and schedule calls to retrieve the attestation token on the same CPU
+ * on which the attestation token generation was initialised.
+ *
+ * The challenge data must be at least 32 bytes and no more than 64 bytes. If
+ * less than 64 bytes are provided it will be zero padded to 64 bytes.
+ *
+ * Return:
+ * * %0        - Attestation token generated successfully.
+ * * %-EINVAL  - A parameter was not valid.
+ * * %-ENOMEM  - Out of memory.
+ * * %-EFAULT  - Failed to get IPA for memory page(s).
+ * * A negative status code as returned by smp_call_function_single().
+ */
+static int arm_cca_report_new(struct tsm_report *report, void *data)
+{
+	int ret;
+	int cpu;
+	long max_size;
+	unsigned long token_size = 0;
+	struct arm_cca_token_info info;
+	void *buf;
+	u8 *token __free(kvfree) = NULL;
+	struct tsm_report_desc *desc = &report->desc;
+
+	if (desc->inblob_len < 32 || desc->inblob_len > 64)
+		return -EINVAL;
+
+	/*
+	 * The attestation token 'init' and 'continue' calls must be
+	 * performed on the same CPU. smp_call_function_single() is used
+	 * instead of simply calling get_cpu() because of the need to
+	 * allocate outblob based on the returned value from the 'init'
+	 * call and that cannot be done in an atomic context.
+	 */
+	cpu = smp_processor_id();
+
+	info.challenge = desc->inblob;
+	info.challenge_size = desc->inblob_len;
+
+	ret = smp_call_function_single(cpu, arm_cca_attestation_init,
+				       &info, true);
+	if (ret)
+		return ret;
+	max_size = info.result;
+
+	if (max_size <= 0)
+		return -EINVAL;
+
+	/* Allocate outblob */
+	token = kvzalloc(max_size, GFP_KERNEL);
+	if (!token)
+		return -ENOMEM;
+
+	/*
+	 * Since the outblob may not be physically contiguous, use a page
+	 * to bounce the buffer from RMM.
+	 */
+	buf = alloc_pages_exact(RSI_GRANULE_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	/* Get the PA of the memory page(s) that were allocated */
+	info.granule = (unsigned long)virt_to_phys(buf);
+
+	/* Loop until the token is ready or there is an error */
+	do {
+		/* Retrieve one RSI_GRANULE_SIZE data per loop iteration */
+		info.offset = 0;
+		do {
+			/*
+			 * Schedule a call to retrieve a sub-granule chunk
+			 * of data per loop iteration.
+			 */
+			ret = smp_call_function_single(cpu,
+						       arm_cca_attestation_continue,
+						       (void *)&info, true);
+			if (ret != 0) {
+				token_size = 0;
+				goto exit_free_granule_page;
+			}
+		} while (info.result == RSI_INCOMPLETE &&
+			 info.offset < RSI_GRANULE_SIZE);
+
+		/* Break out in case of failure */
+		if (info.result != RSI_SUCCESS && info.result != RSI_INCOMPLETE) {
+			ret = -ENXIO;
+			token_size = 0;
+			goto exit_free_granule_page;
+		}
+
+		/*
+		 * Copy the retrieved token data from the granule
+		 * to the token buffer, ensuring that the RMM doesn't
+		 * overflow the buffer.
+		 */
+		if (WARN_ON(token_size + info.offset > max_size))
+			break;
+		memcpy(&token[token_size], buf, info.offset);
+		token_size += info.offset;
+	} while (info.result == RSI_INCOMPLETE);
+
+	report->outblob = no_free_ptr(token);
+exit_free_granule_page:
+	report->outblob_len = token_size;
+	free_pages_exact(buf, RSI_GRANULE_SIZE);
+	return ret;
+}
+
+static const struct tsm_report_ops arm_cca_tsm_ops = {
+	.name = KBUILD_MODNAME,
+	.report_new = arm_cca_report_new,
+};
+
+/**
+ * arm_cca_guest_init - Register with the Trusted Security Module (TSM)
+ * interface.
+ *
+ * Return:
+ * * %0        - Registered successfully with the TSM interface.
+ * * %-ENODEV  - The execution context is not an Arm Realm.
+ * * %-EBUSY   - Already registered.
+ */
+static int __init arm_cca_guest_init(void)
+{
+	int ret;
+
+	if (!is_realm_world())
+		return -ENODEV;
+
+	ret = tsm_report_register(&arm_cca_tsm_ops, NULL);
+	if (ret < 0)
+		pr_err("Error %d registering with TSM\n", ret);
+
+	return ret;
+}
+module_init(arm_cca_guest_init);
+
+/**
+ * arm_cca_guest_exit - unregister with the Trusted Security Module (TSM)
+ * interface.
+ */
+static void __exit arm_cca_guest_exit(void)
+{
+	tsm_report_unregister(&arm_cca_tsm_ops);
+}
+module_exit(arm_cca_guest_exit);
+
+/* modalias, so userspace can autoload this module when RSI is available */
+static const struct platform_device_id arm_cca_match[] __maybe_unused = {
+	{ RSI_PDEV_NAME, 0},
+	{ }
+};
+
+MODULE_DEVICE_TABLE(platform, arm_cca_match);
+MODULE_AUTHOR("Sami Mujawar <sami.mujawar@arm.com>");
+MODULE_DESCRIPTION("Arm CCA Guest TSM Driver");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/virt/coco/efi_secret/Kconfig

@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config EFI_SECRET
+	tristate "EFI secret area securityfs support"
+	depends on EFI && (X86_64 || ARM64)
+	select EFI_COCO_SECRET
+	select SECURITYFS
+	help
+	  This is a driver for accessing the EFI secret area via securityfs.
+	  The EFI secret area is a memory area designated by the firmware for
+	  confidential computing secret injection (for example for AMD SEV
+	  guests).  The driver exposes the secrets as files in
+	  <securityfs>/secrets/coco.  Files can be read and deleted (deleting
+	  a file wipes the secret from memory).
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called efi_secret.

linux-7.2.3/drivers/virt/coco/efi_secret/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_EFI_SECRET) += efi_secret.o

linux-7.2.3/drivers/virt/coco/efi_secret/efi_secret.c

@@ -0,0 +1,319 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * efi_secret module
+ *
+ * Copyright (C) 2022 IBM Corporation
+ * Author: Dov Murik <dovmurik@linux.ibm.com>
+ */
+
+/**
+ * DOC: efi_secret: Allow reading EFI confidential computing (coco) secret area
+ * via securityfs interface.
+ *
+ * When the module is loaded (and securityfs is mounted, typically under
+ * /sys/kernel/security), a "secrets/coco" directory is created in securityfs.
+ * In it, a file is created for each secret entry.  The name of each such file
+ * is the GUID of the secret entry, and its content is the secret data.
+ */
+
+#include <linux/platform_device.h>
+#include <linux/seq_file.h>
+#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/io.h>
+#include <linux/security.h>
+#include <linux/efi.h>
+#include <linux/cacheflush.h>
+
+#define EFI_SECRET_NUM_FILES 64
+
+struct efi_secret {
+	struct dentry *secrets_dir;
+	void __iomem *secret_data;
+	u64 secret_data_len;
+};
+
+/*
+ * Structure of the EFI secret area
+ *
+ * Offset   Length
+ * (bytes)  (bytes)  Usage
+ * -------  -------  -----
+ *       0       16  Secret table header GUID (must be 1e74f542-71dd-4d66-963e-ef4287ff173b)
+ *      16        4  Length of bytes of the entire secret area
+ *
+ *      20       16  First secret entry's GUID
+ *      36        4  First secret entry's length in bytes (= 16 + 4 + x)
+ *      40        x  First secret entry's data
+ *
+ *    40+x       16  Second secret entry's GUID
+ *    56+x        4  Second secret entry's length in bytes (= 16 + 4 + y)
+ *    60+x        y  Second secret entry's data
+ *
+ * (... and so on for additional entries)
+ *
+ * The GUID of each secret entry designates the usage of the secret data.
+ */
+
+/**
+ * struct secret_header - Header of entire secret area; this should be followed
+ * by instances of struct secret_entry.
+ * @guid:	Must be EFI_SECRET_TABLE_HEADER_GUID
+ * @len:	Length in bytes of entire secret area, including header
+ */
+struct secret_header {
+	efi_guid_t guid;
+	u32 len;
+} __attribute((packed));
+
+/**
+ * struct secret_entry - Holds one secret entry
+ * @guid:	Secret-specific GUID (or NULL_GUID if this secret entry was deleted)
+ * @len:	Length of secret entry, including its guid and len fields
+ * @data:	The secret data (full of zeros if this secret entry was deleted)
+ */
+struct secret_entry {
+	efi_guid_t guid;
+	u32 len;
+	u8 data[];
+} __attribute((packed));
+
+static size_t secret_entry_data_len(struct secret_entry *e)
+{
+	return e->len - sizeof(*e);
+}
+
+static struct efi_secret the_efi_secret;
+
+static inline struct efi_secret *efi_secret_get(void)
+{
+	return &the_efi_secret;
+}
+
+static int efi_secret_bin_file_show(struct seq_file *file, void *data)
+{
+	struct secret_entry *e = file->private;
+
+	if (e)
+		seq_write(file, e->data, secret_entry_data_len(e));
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(efi_secret_bin_file);
+
+/*
+ * Overwrite memory content with zeroes, and ensure that dirty cache lines are
+ * actually written back to memory, to clear out the secret.
+ */
+static void wipe_memory(void *addr, size_t size)
+{
+	memzero_explicit(addr, size);
+#ifdef CONFIG_X86
+	clflush_cache_range(addr, size);
+#endif
+}
+
+static int efi_secret_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = d_inode(dentry);
+	struct secret_entry *e = (struct secret_entry *)inode->i_private;
+
+	if (e) {
+		/* Zero out the secret data */
+		wipe_memory(e->data, secret_entry_data_len(e));
+		e->guid = NULL_GUID;
+	}
+
+	inode->i_private = NULL;
+
+	return simple_unlink(inode, dentry);
+}
+
+static const struct inode_operations efi_secret_dir_inode_operations = {
+	.lookup         = simple_lookup,
+	.unlink         = efi_secret_unlink,
+};
+
+static int efi_secret_map_area(struct platform_device *dev)
+{
+	int ret;
+	struct efi_secret *s = efi_secret_get();
+	struct linux_efi_coco_secret_area *secret_area;
+
+	if (efi.coco_secret == EFI_INVALID_TABLE_ADDR) {
+		dev_err(&dev->dev, "Secret area address is not available\n");
+		return -EINVAL;
+	}
+
+	secret_area = memremap(efi.coco_secret, sizeof(*secret_area), MEMREMAP_WB);
+	if (secret_area == NULL) {
+		dev_err(&dev->dev, "Could not map secret area EFI config entry\n");
+		return -ENOMEM;
+	}
+	if (!secret_area->base_pa || secret_area->size < sizeof(struct secret_header)) {
+		dev_err(&dev->dev,
+			"Invalid secret area memory location (base_pa=0x%llx size=0x%llx)\n",
+			secret_area->base_pa, secret_area->size);
+		ret = -EINVAL;
+		goto unmap;
+	}
+
+	s->secret_data = ioremap_encrypted(secret_area->base_pa, secret_area->size);
+	if (s->secret_data == NULL) {
+		dev_err(&dev->dev, "Could not map secret area\n");
+		ret = -ENOMEM;
+		goto unmap;
+	}
+
+	s->secret_data_len = secret_area->size;
+	ret = 0;
+
+unmap:
+	memunmap(secret_area);
+	return ret;
+}
+
+static void efi_secret_securityfs_teardown(struct platform_device *dev)
+{
+	struct efi_secret *s = efi_secret_get();
+
+	securityfs_remove(s->secrets_dir);
+	s->secrets_dir = NULL;
+
+	dev_dbg(&dev->dev, "Removed securityfs entries\n");
+}
+
+static int efi_secret_securityfs_setup(struct platform_device *dev)
+{
+	struct efi_secret *s = efi_secret_get();
+	int ret = 0, i = 0, bytes_left;
+	unsigned char *ptr;
+	struct secret_header *h;
+	struct secret_entry *e;
+	struct dentry *dent, *dir;
+	char guid_str[EFI_VARIABLE_GUID_LEN + 1];
+
+	ptr = (void __force *)s->secret_data;
+	h = (struct secret_header *)ptr;
+	if (efi_guidcmp(h->guid, EFI_SECRET_TABLE_HEADER_GUID)) {
+		/*
+		 * This is not an error: it just means that EFI defines secret
+		 * area but it was not populated by the Guest Owner.
+		 */
+		dev_dbg(&dev->dev, "EFI secret area does not start with correct GUID\n");
+		return -ENODEV;
+	}
+	if (h->len < sizeof(*h)) {
+		dev_err(&dev->dev, "EFI secret area reported length is too small\n");
+		return -EINVAL;
+	}
+	if (h->len > s->secret_data_len) {
+		dev_err(&dev->dev, "EFI secret area reported length is too big\n");
+		return -EINVAL;
+	}
+
+	s->secrets_dir = NULL;
+
+	dent = securityfs_create_dir("secrets", NULL);
+	if (IS_ERR(dent)) {
+		dev_err(&dev->dev, "Error creating secrets securityfs directory entry err=%ld\n",
+			PTR_ERR(dent));
+		return PTR_ERR(dent);
+	}
+	s->secrets_dir = dent;
+
+	dir = securityfs_create_dir("coco", s->secrets_dir);
+	if (IS_ERR(dir)) {
+		dev_err(&dev->dev, "Error creating coco securityfs directory entry err=%ld\n",
+			PTR_ERR(dir));
+		return PTR_ERR(dir);
+	}
+	d_inode(dir)->i_op = &efi_secret_dir_inode_operations;
+
+	bytes_left = h->len - sizeof(*h);
+	ptr += sizeof(*h);
+	while (bytes_left >= (int)sizeof(*e) && i < EFI_SECRET_NUM_FILES) {
+		e = (struct secret_entry *)ptr;
+		if (e->len < sizeof(*e) || e->len > (unsigned int)bytes_left) {
+			dev_err(&dev->dev, "EFI secret area is corrupted\n");
+			ret = -EINVAL;
+			goto err_cleanup;
+		}
+
+		/* Skip deleted entries (which will have NULL_GUID) */
+		if (efi_guidcmp(e->guid, NULL_GUID)) {
+			efi_guid_to_str(&e->guid, guid_str);
+
+			dent = securityfs_create_file(guid_str, 0440, dir, (void *)e,
+						      &efi_secret_bin_file_fops);
+			if (IS_ERR(dent)) {
+				dev_err(&dev->dev, "Error creating efi_secret securityfs entry\n");
+				ret = PTR_ERR(dent);
+				goto err_cleanup;
+			}
+			i++;
+		}
+		ptr += e->len;
+		bytes_left -= e->len;
+	}
+
+	dev_info(&dev->dev, "Created %d entries in securityfs secrets/coco\n", i);
+	return 0;
+
+err_cleanup:
+	efi_secret_securityfs_teardown(dev);
+	return ret;
+}
+
+static void efi_secret_unmap_area(void)
+{
+	struct efi_secret *s = efi_secret_get();
+
+	if (s->secret_data) {
+		iounmap(s->secret_data);
+		s->secret_data = NULL;
+		s->secret_data_len = 0;
+	}
+}
+
+static int efi_secret_probe(struct platform_device *dev)
+{
+	int ret;
+
+	ret = efi_secret_map_area(dev);
+	if (ret)
+		return ret;
+
+	ret = efi_secret_securityfs_setup(dev);
+	if (ret)
+		goto err_unmap;
+
+	return ret;
+
+err_unmap:
+	efi_secret_unmap_area();
+	return ret;
+}
+
+static void efi_secret_remove(struct platform_device *dev)
+{
+	efi_secret_securityfs_teardown(dev);
+	efi_secret_unmap_area();
+}
+
+static struct platform_driver efi_secret_driver = {
+	.probe = efi_secret_probe,
+	.remove = efi_secret_remove,
+	.driver = {
+		.name = "efi_secret",
+	},
+};
+
+module_platform_driver(efi_secret_driver);
+
+MODULE_DESCRIPTION("Confidential computing EFI secret area access");
+MODULE_AUTHOR("IBM");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:efi_secret");

linux-7.2.3/drivers/virt/coco/guest/Kconfig

@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Confidential computing shared guest collateral
+#
+config TSM_GUEST
+	bool
+
+config TSM_REPORTS
+	select TSM_GUEST
+	select CONFIGFS_FS
+	tristate
+
+config TSM_MEASUREMENTS
+	select TSM_GUEST
+	select CRYPTO_HASH_INFO
+	bool

linux-7.2.3/drivers/virt/coco/guest/Makefile

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_TSM_REPORTS)	+= tsm_report.o
+tsm_report-y := report.o
+obj-$(CONFIG_TSM_MEASUREMENTS)	+= tsm-mr.o

linux-7.2.3/drivers/virt/coco/guest/report.c

@@ -0,0 +1,539 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2023 Intel Corporation. All rights reserved. */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/tsm.h>
+#include <linux/err.h>
+#include <linux/slab.h>
+#include <linux/rwsem.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/cleanup.h>
+#include <linux/configfs.h>
+
+static struct tsm_provider {
+	const struct tsm_report_ops *ops;
+	void *data;
+	atomic_t count;
+} provider;
+static DECLARE_RWSEM(tsm_rwsem);
+
+/**
+ * DOC: Trusted Security Module (TSM) Attestation Report Interface
+ *
+ * The TSM report interface is a common provider of blobs that facilitate
+ * attestation of a TVM (confidential computing guest) by an attestation
+ * service. A TSM report combines a user-defined blob (likely a public-key with
+ * a nonce for a key-exchange protocol) with a signed attestation report. That
+ * combined blob is then used to obtain secrets provided by an agent that can
+ * validate the attestation report. The expectation is that this interface is
+ * invoked infrequently, however configfs allows for multiple agents to
+ * own their own report generation instances to generate reports as
+ * often as needed.
+ *
+ * The attestation report format is TSM provider specific, when / if a standard
+ * materializes that can be published instead of the vendor layout. Until then
+ * the 'provider' attribute indicates the format of 'outblob', and optionally
+ * 'auxblob' and 'manifestblob'.
+ */
+
+struct tsm_report_state {
+	struct tsm_report report;
+	unsigned long write_generation;
+	unsigned long read_generation;
+	struct config_item cfg;
+};
+
+enum tsm_data_select {
+	TSM_REPORT,
+	TSM_CERTS,
+	TSM_MANIFEST,
+};
+
+static struct tsm_report *to_tsm_report(struct config_item *cfg)
+{
+	struct tsm_report_state *state =
+		container_of(cfg, struct tsm_report_state, cfg);
+
+	return &state->report;
+}
+
+static struct tsm_report_state *to_state(struct tsm_report *report)
+{
+	return container_of(report, struct tsm_report_state, report);
+}
+
+static int try_advance_write_generation(struct tsm_report *report)
+{
+	struct tsm_report_state *state = to_state(report);
+
+	lockdep_assert_held_write(&tsm_rwsem);
+
+	/*
+	 * Malicious or broken userspace has written enough times for
+	 * read_generation == write_generation by modular arithmetic without an
+	 * interim read. Stop accepting updates until the current report
+	 * configuration is read.
+	 */
+	if (state->write_generation == state->read_generation - 1)
+		return -EBUSY;
+	state->write_generation++;
+	return 0;
+}
+
+static ssize_t tsm_report_privlevel_store(struct config_item *cfg,
+					  const char *buf, size_t len)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+	unsigned int val;
+	int rc;
+
+	rc = kstrtouint(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	guard(rwsem_write)(&tsm_rwsem);
+	if (!provider.ops)
+		return -ENXIO;
+
+	/*
+	 * The valid privilege levels that a TSM might accept, if it accepts a
+	 * privilege level setting at all, are a max of TSM_PRIVLEVEL_MAX (see
+	 * SEV-SNP GHCB) and a minimum of a TSM selected floor value no less
+	 * than 0.
+	 */
+	if (provider.ops->privlevel_floor > val || val > TSM_REPORT_PRIVLEVEL_MAX)
+		return -EINVAL;
+
+	rc = try_advance_write_generation(report);
+	if (rc)
+		return rc;
+	report->desc.privlevel = val;
+
+	return len;
+}
+CONFIGFS_ATTR_WO(tsm_report_, privlevel);
+
+static ssize_t tsm_report_privlevel_floor_show(struct config_item *cfg,
+					       char *buf)
+{
+	guard(rwsem_read)(&tsm_rwsem);
+
+	if (!provider.ops)
+		return -ENXIO;
+
+	return sysfs_emit(buf, "%u\n", provider.ops->privlevel_floor);
+}
+CONFIGFS_ATTR_RO(tsm_report_, privlevel_floor);
+
+static ssize_t tsm_report_service_provider_store(struct config_item *cfg,
+						 const char *buf, size_t len)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+	size_t sp_len;
+	char *sp;
+	int rc;
+
+	guard(rwsem_write)(&tsm_rwsem);
+	rc = try_advance_write_generation(report);
+	if (rc)
+		return rc;
+
+	sp_len = (buf[len - 1] != '\n') ? len : len - 1;
+
+	sp = kstrndup(buf, sp_len, GFP_KERNEL);
+	if (!sp)
+		return -ENOMEM;
+	kfree(report->desc.service_provider);
+
+	report->desc.service_provider = sp;
+
+	return len;
+}
+CONFIGFS_ATTR_WO(tsm_report_, service_provider);
+
+static ssize_t tsm_report_service_guid_store(struct config_item *cfg,
+					     const char *buf, size_t len)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+	int rc;
+
+	guard(rwsem_write)(&tsm_rwsem);
+	rc = try_advance_write_generation(report);
+	if (rc)
+		return rc;
+
+	report->desc.service_guid = guid_null;
+
+	rc = guid_parse(buf, &report->desc.service_guid);
+	if (rc)
+		return rc;
+
+	return len;
+}
+CONFIGFS_ATTR_WO(tsm_report_, service_guid);
+
+static ssize_t tsm_report_service_manifest_version_store(struct config_item *cfg,
+							 const char *buf, size_t len)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+	unsigned int val;
+	int rc;
+
+	rc = kstrtouint(buf, 0, &val);
+	if (rc)
+		return rc;
+
+	guard(rwsem_write)(&tsm_rwsem);
+	rc = try_advance_write_generation(report);
+	if (rc)
+		return rc;
+	report->desc.service_manifest_version = val;
+
+	return len;
+}
+CONFIGFS_ATTR_WO(tsm_report_, service_manifest_version);
+
+static ssize_t tsm_report_inblob_write(struct config_item *cfg,
+				       const void *buf, size_t count)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+	int rc;
+
+	guard(rwsem_write)(&tsm_rwsem);
+	rc = try_advance_write_generation(report);
+	if (rc)
+		return rc;
+
+	report->desc.inblob_len = count;
+	memcpy(report->desc.inblob, buf, count);
+	return count;
+}
+CONFIGFS_BIN_ATTR_WO(tsm_report_, inblob, NULL, TSM_REPORT_INBLOB_MAX);
+
+static ssize_t tsm_report_generation_show(struct config_item *cfg, char *buf)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+	struct tsm_report_state *state = to_state(report);
+
+	guard(rwsem_read)(&tsm_rwsem);
+	return sysfs_emit(buf, "%lu\n", state->write_generation);
+}
+CONFIGFS_ATTR_RO(tsm_report_, generation);
+
+static ssize_t tsm_report_provider_show(struct config_item *cfg, char *buf)
+{
+	guard(rwsem_read)(&tsm_rwsem);
+	if (!provider.ops)
+		return -ENXIO;
+
+	return sysfs_emit(buf, "%s\n", provider.ops->name);
+}
+CONFIGFS_ATTR_RO(tsm_report_, provider);
+
+static ssize_t __read_report(struct tsm_report *report, void *buf, size_t count,
+			     enum tsm_data_select select)
+{
+	loff_t offset = 0;
+	ssize_t len;
+	u8 *out;
+
+	if (select == TSM_REPORT) {
+		out = report->outblob;
+		len = report->outblob_len;
+	} else if (select == TSM_MANIFEST) {
+		out = report->manifestblob;
+		len = report->manifestblob_len;
+	} else {
+		out = report->auxblob;
+		len = report->auxblob_len;
+	}
+
+	/*
+	 * Recall that a NULL @buf is configfs requesting the size of
+	 * the buffer.
+	 */
+	if (!buf)
+		return len;
+	return memory_read_from_buffer(buf, count, &offset, out, len);
+}
+
+static ssize_t read_cached_report(struct tsm_report *report, void *buf,
+				  size_t count, enum tsm_data_select select)
+{
+	struct tsm_report_state *state = to_state(report);
+
+	guard(rwsem_read)(&tsm_rwsem);
+	if (!report->desc.inblob_len)
+		return -EINVAL;
+
+	/*
+	 * A given TSM backend always fills in ->outblob regardless of
+	 * whether the report includes an auxblob/manifestblob or not.
+	 */
+	if (!report->outblob ||
+	    state->read_generation != state->write_generation)
+		return -EWOULDBLOCK;
+
+	return __read_report(report, buf, count, select);
+}
+
+static ssize_t tsm_report_read(struct tsm_report *report, void *buf,
+			       size_t count, enum tsm_data_select select)
+{
+	struct tsm_report_state *state = to_state(report);
+	const struct tsm_report_ops *ops;
+	ssize_t rc;
+
+	/* try to read from the existing report if present and valid... */
+	rc = read_cached_report(report, buf, count, select);
+	if (rc >= 0 || rc != -EWOULDBLOCK)
+		return rc;
+
+	/* slow path, report may need to be regenerated... */
+	guard(rwsem_write)(&tsm_rwsem);
+	ops = provider.ops;
+	if (!ops)
+		return -ENXIO;
+	if (!report->desc.inblob_len)
+		return -EINVAL;
+
+	/* did another thread already generate this report? */
+	if (report->outblob &&
+	    state->read_generation == state->write_generation)
+		goto out;
+
+	kvfree(report->outblob);
+	kvfree(report->auxblob);
+	kvfree(report->manifestblob);
+	report->outblob = NULL;
+	report->auxblob = NULL;
+	report->manifestblob = NULL;
+	rc = ops->report_new(report, provider.data);
+	if (rc < 0)
+		return rc;
+	state->read_generation = state->write_generation;
+out:
+	return __read_report(report, buf, count, select);
+}
+
+static ssize_t tsm_report_outblob_read(struct config_item *cfg, void *buf,
+				       size_t count)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+
+	return tsm_report_read(report, buf, count, TSM_REPORT);
+}
+CONFIGFS_BIN_ATTR_RO(tsm_report_, outblob, NULL, TSM_REPORT_OUTBLOB_MAX);
+
+static ssize_t tsm_report_auxblob_read(struct config_item *cfg, void *buf,
+				       size_t count)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+
+	return tsm_report_read(report, buf, count, TSM_CERTS);
+}
+CONFIGFS_BIN_ATTR_RO(tsm_report_, auxblob, NULL, TSM_REPORT_OUTBLOB_MAX);
+
+static ssize_t tsm_report_manifestblob_read(struct config_item *cfg, void *buf,
+					    size_t count)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+
+	return tsm_report_read(report, buf, count, TSM_MANIFEST);
+}
+CONFIGFS_BIN_ATTR_RO(tsm_report_, manifestblob, NULL, TSM_REPORT_OUTBLOB_MAX);
+
+static struct configfs_attribute *tsm_report_attrs[] = {
+	[TSM_REPORT_GENERATION] = &tsm_report_attr_generation,
+	[TSM_REPORT_PROVIDER] = &tsm_report_attr_provider,
+	[TSM_REPORT_PRIVLEVEL] = &tsm_report_attr_privlevel,
+	[TSM_REPORT_PRIVLEVEL_FLOOR] = &tsm_report_attr_privlevel_floor,
+	[TSM_REPORT_SERVICE_PROVIDER] = &tsm_report_attr_service_provider,
+	[TSM_REPORT_SERVICE_GUID] = &tsm_report_attr_service_guid,
+	[TSM_REPORT_SERVICE_MANIFEST_VER] = &tsm_report_attr_service_manifest_version,
+	NULL,
+};
+
+static struct configfs_bin_attribute *tsm_report_bin_attrs[] = {
+	[TSM_REPORT_INBLOB] = &tsm_report_attr_inblob,
+	[TSM_REPORT_OUTBLOB] = &tsm_report_attr_outblob,
+	[TSM_REPORT_AUXBLOB] = &tsm_report_attr_auxblob,
+	[TSM_REPORT_MANIFESTBLOB] = &tsm_report_attr_manifestblob,
+	NULL,
+};
+
+static void tsm_report_item_release(struct config_item *cfg)
+{
+	struct tsm_report *report = to_tsm_report(cfg);
+	struct tsm_report_state *state = to_state(report);
+
+	kvfree(report->manifestblob);
+	kvfree(report->auxblob);
+	kvfree(report->outblob);
+	kfree(report->desc.service_provider);
+	kfree(state);
+}
+
+static struct configfs_item_operations tsm_report_item_ops = {
+	.release = tsm_report_item_release,
+};
+
+static bool tsm_report_is_visible(struct config_item *item,
+				  struct configfs_attribute *attr, int n)
+{
+	guard(rwsem_read)(&tsm_rwsem);
+	if (!provider.ops)
+		return false;
+
+	if (!provider.ops->report_attr_visible)
+		return true;
+
+	return provider.ops->report_attr_visible(n);
+}
+
+static bool tsm_report_is_bin_visible(struct config_item *item,
+				      struct configfs_bin_attribute *attr, int n)
+{
+	guard(rwsem_read)(&tsm_rwsem);
+	if (!provider.ops)
+		return false;
+
+	if (!provider.ops->report_bin_attr_visible)
+		return true;
+
+	return provider.ops->report_bin_attr_visible(n);
+}
+
+static struct configfs_group_operations tsm_report_attr_group_ops = {
+	.is_visible = tsm_report_is_visible,
+	.is_bin_visible = tsm_report_is_bin_visible,
+};
+
+static const struct config_item_type tsm_report_type = {
+	.ct_owner = THIS_MODULE,
+	.ct_bin_attrs = tsm_report_bin_attrs,
+	.ct_attrs = tsm_report_attrs,
+	.ct_item_ops = &tsm_report_item_ops,
+	.ct_group_ops = &tsm_report_attr_group_ops,
+};
+
+static struct config_item *tsm_report_make_item(struct config_group *group,
+						const char *name)
+{
+	struct tsm_report_state *state;
+
+	guard(rwsem_read)(&tsm_rwsem);
+	if (!provider.ops)
+		return ERR_PTR(-ENXIO);
+
+	state = kzalloc_obj(*state);
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	atomic_inc(&provider.count);
+	config_item_init_type_name(&state->cfg, name, &tsm_report_type);
+	return &state->cfg;
+}
+
+static void tsm_report_drop_item(struct config_group *group, struct config_item *item)
+{
+	config_item_put(item);
+	atomic_dec(&provider.count);
+}
+
+static struct configfs_group_operations tsm_report_group_ops = {
+	.make_item = tsm_report_make_item,
+	.drop_item = tsm_report_drop_item,
+};
+
+static const struct config_item_type tsm_reports_type = {
+	.ct_owner = THIS_MODULE,
+	.ct_group_ops = &tsm_report_group_ops,
+};
+
+static const struct config_item_type tsm_root_group_type = {
+	.ct_owner = THIS_MODULE,
+};
+
+static struct configfs_subsystem tsm_configfs = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf = "tsm",
+			.ci_type = &tsm_root_group_type,
+		},
+	},
+	.su_mutex = __MUTEX_INITIALIZER(tsm_configfs.su_mutex),
+};
+
+int tsm_report_register(const struct tsm_report_ops *ops, void *priv)
+{
+	const struct tsm_report_ops *conflict;
+
+	guard(rwsem_write)(&tsm_rwsem);
+	conflict = provider.ops;
+	if (conflict) {
+		pr_err("\"%s\" ops already registered\n", conflict->name);
+		return -EBUSY;
+	}
+
+	if (atomic_read(&provider.count)) {
+		pr_err("configfs/tsm/report not empty\n");
+		return -EBUSY;
+	}
+
+	provider.ops = ops;
+	provider.data = priv;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tsm_report_register);
+
+int tsm_report_unregister(const struct tsm_report_ops *ops)
+{
+	guard(rwsem_write)(&tsm_rwsem);
+	if (ops != provider.ops)
+		return -EBUSY;
+	if (atomic_read(&provider.count))
+		pr_warn("\"%s\" unregistered with items present in configfs/tsm/report\n",
+			provider.ops->name);
+	provider.ops = NULL;
+	provider.data = NULL;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tsm_report_unregister);
+
+static struct config_group *tsm_report_group;
+
+static int __init tsm_report_init(void)
+{
+	struct config_group *root = &tsm_configfs.su_group;
+	struct config_group *tsm;
+	int rc;
+
+	config_group_init(root);
+	rc = configfs_register_subsystem(&tsm_configfs);
+	if (rc)
+		return rc;
+
+	tsm = configfs_register_default_group(root, "report",
+					      &tsm_reports_type);
+	if (IS_ERR(tsm)) {
+		configfs_unregister_subsystem(&tsm_configfs);
+		return PTR_ERR(tsm);
+	}
+	tsm_report_group = tsm;
+
+	return 0;
+}
+module_init(tsm_report_init);
+
+static void __exit tsm_report_exit(void)
+{
+	configfs_unregister_default_group(tsm_report_group);
+	configfs_unregister_subsystem(&tsm_configfs);
+}
+module_exit(tsm_report_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Provide Trusted Security Module attestation reports via configfs");

linux-7.2.3/drivers/virt/coco/guest/tsm-mr.c

@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2024-2025 Intel Corporation. All rights reserved. */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/sysfs.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/tsm_mr.h>
+
+/*
+ * struct tm_context - contains everything necessary to implement sysfs
+ * attributes for MRs.
+ * @rwsem: protects the MR cache from concurrent access.
+ * @agrp: contains all MR attributes created by tsm_mr_create_attribute_group().
+ * @tm: input to tsm_mr_create_attribute_group() containing MR definitions/ops.
+ * @in_sync: %true if MR cache is up-to-date.
+ * @mrs: array of &struct bin_attribute, one for each MR.
+ *
+ * This internal structure contains everything needed to implement
+ * tm_digest_read() and tm_digest_write().
+ *
+ * Given tm->refresh() is potentially expensive, tm_digest_read() caches MR
+ * values and calls tm->refresh() only when necessary. Only live MRs (i.e., with
+ * %TSM_MR_F_LIVE set) can trigger tm->refresh(), while others are assumed to
+ * retain their values from the last tm->write(). @in_sync tracks if there have
+ * been tm->write() calls since the last tm->refresh(). That is, tm->refresh()
+ * will be called only when a live MR is being read and the cache is stale
+ * (@in_sync is %false).
+ *
+ * tm_digest_write() sets @in_sync to %false and calls tm->write(), whose
+ * semantics is arch and MR specific. Most (if not all) writable MRs support the
+ * extension semantics (i.e., tm->write() extends the input buffer into the MR).
+ */
+struct tm_context {
+	struct rw_semaphore rwsem;
+	struct attribute_group agrp;
+	const struct tsm_measurements *tm;
+	bool in_sync;
+	struct bin_attribute mrs[];
+};
+
+static ssize_t tm_digest_read(struct file *filp, struct kobject *kobj,
+			      const struct bin_attribute *attr, char *buffer,
+			      loff_t off, size_t count)
+{
+	struct tm_context *ctx;
+	const struct tsm_measurement_register *mr;
+	int rc;
+
+	ctx = attr->private;
+	rc = down_read_interruptible(&ctx->rwsem);
+	if (rc)
+		return rc;
+
+	mr = &ctx->tm->mrs[attr - ctx->mrs];
+
+	/*
+	 * @ctx->in_sync indicates if the MR cache is stale. It is a global
+	 * instead of a per-MR flag for simplicity, as most (if not all) archs
+	 * allow reading all MRs in oneshot.
+	 *
+	 * ctx->refresh() is necessary only for LIVE MRs, while others retain
+	 * their values from their respective last ctx->write().
+	 */
+	if ((mr->mr_flags & TSM_MR_F_LIVE) && !ctx->in_sync) {
+		up_read(&ctx->rwsem);
+
+		rc = down_write_killable(&ctx->rwsem);
+		if (rc)
+			return rc;
+
+		if (!ctx->in_sync) {
+			rc = ctx->tm->refresh(ctx->tm);
+			ctx->in_sync = !rc;
+			trace_tsm_mr_refresh(mr, rc);
+		}
+
+		downgrade_write(&ctx->rwsem);
+	}
+
+	memcpy(buffer, mr->mr_value + off, count);
+	trace_tsm_mr_read(mr);
+
+	up_read(&ctx->rwsem);
+	return rc ?: count;
+}
+
+static ssize_t tm_digest_write(struct file *filp, struct kobject *kobj,
+			       const struct bin_attribute *attr, char *buffer,
+			       loff_t off, size_t count)
+{
+	struct tm_context *ctx;
+	const struct tsm_measurement_register *mr;
+	ssize_t rc;
+
+	/* partial writes are not supported */
+	if (off != 0 || count != attr->size)
+		return -EINVAL;
+
+	ctx = attr->private;
+	mr = &ctx->tm->mrs[attr - ctx->mrs];
+
+	rc = down_write_killable(&ctx->rwsem);
+	if (rc)
+		return rc;
+
+	rc = ctx->tm->write(ctx->tm, mr, buffer);
+
+	/* mark MR cache stale */
+	if (!rc) {
+		ctx->in_sync = false;
+		trace_tsm_mr_write(mr, buffer);
+	}
+
+	up_write(&ctx->rwsem);
+	return rc ?: count;
+}
+
+/**
+ * tsm_mr_create_attribute_group() - creates an attribute group for measurement
+ * registers (MRs)
+ * @tm: pointer to &struct tsm_measurements containing the MR definitions.
+ *
+ * This function creates attributes corresponding to the MR definitions
+ * provided by @tm->mrs.
+ *
+ * The created attributes will reference @tm and its members. The caller must
+ * not free @tm until after tsm_mr_free_attribute_group() is called.
+ *
+ * Context: Process context. May sleep due to memory allocation.
+ *
+ * Return:
+ * * On success, the pointer to a an attribute group is returned; otherwise
+ * * %-EINVAL - Invalid MR definitions.
+ * * %-ENOMEM - Out of memory.
+ */
+const struct attribute_group *
+tsm_mr_create_attribute_group(const struct tsm_measurements *tm)
+{
+	size_t nlen;
+
+	if (!tm || !tm->mrs)
+		return ERR_PTR(-EINVAL);
+
+	/* aggregated length of all MR names */
+	nlen = 0;
+	for (size_t i = 0; i < tm->nr_mrs; ++i) {
+		if ((tm->mrs[i].mr_flags & TSM_MR_F_LIVE) && !tm->refresh)
+			return ERR_PTR(-EINVAL);
+
+		if ((tm->mrs[i].mr_flags & TSM_MR_F_WRITABLE) && !tm->write)
+			return ERR_PTR(-EINVAL);
+
+		if (!tm->mrs[i].mr_name)
+			return ERR_PTR(-EINVAL);
+
+		if (tm->mrs[i].mr_flags & TSM_MR_F_NOHASH)
+			continue;
+
+		if (tm->mrs[i].mr_hash >= HASH_ALGO__LAST)
+			return ERR_PTR(-EINVAL);
+
+		/* MR sysfs attribute names have the form of MRNAME:HASH */
+		nlen += strlen(tm->mrs[i].mr_name) + 1 +
+			strlen(hash_algo_name[tm->mrs[i].mr_hash]) + 1;
+	}
+
+	/*
+	 * @attrs and the MR name strings are combined into a single allocation
+	 * so that we don't have to free MR names one-by-one in
+	 * tsm_mr_free_attribute_group()
+	 */
+	const struct bin_attribute **attrs __free(kfree) =
+		kzalloc(sizeof(*attrs) * (tm->nr_mrs + 1) + nlen, GFP_KERNEL);
+	struct tm_context *ctx __free(kfree) =
+		kzalloc_flex(*ctx, mrs, tm->nr_mrs);
+	char *name, *end;
+
+	if (!ctx || !attrs)
+		return ERR_PTR(-ENOMEM);
+
+	/* @attrs is followed immediately by MR name strings */
+	name = (char *)&attrs[tm->nr_mrs + 1];
+	end = name + nlen;
+
+	for (size_t i = 0; i < tm->nr_mrs; ++i) {
+		struct bin_attribute *bap = &ctx->mrs[i];
+
+		sysfs_bin_attr_init(bap);
+
+		if (tm->mrs[i].mr_flags & TSM_MR_F_NOHASH)
+			bap->attr.name = tm->mrs[i].mr_name;
+		else if (name < end) {
+			bap->attr.name = name;
+			name += snprintf(name, end - name, "%s:%s",
+					 tm->mrs[i].mr_name,
+					 hash_algo_name[tm->mrs[i].mr_hash]);
+			++name;
+		} else
+			return ERR_PTR(-EINVAL);
+
+		/* check for duplicated MR definitions */
+		for (size_t j = 0; j < i; ++j)
+			if (!strcmp(bap->attr.name, attrs[j]->attr.name))
+				return ERR_PTR(-EINVAL);
+
+		if (tm->mrs[i].mr_flags & TSM_MR_F_READABLE) {
+			bap->attr.mode |= 0444;
+			bap->read = tm_digest_read;
+		}
+
+		if (tm->mrs[i].mr_flags & TSM_MR_F_WRITABLE) {
+			bap->attr.mode |= 0200;
+			bap->write = tm_digest_write;
+		}
+
+		bap->size = tm->mrs[i].mr_size;
+		bap->private = ctx;
+
+		attrs[i] = bap;
+	}
+
+	if (name != end)
+		return ERR_PTR(-EINVAL);
+
+	init_rwsem(&ctx->rwsem);
+	ctx->agrp.name = "measurements";
+	ctx->agrp.bin_attrs = no_free_ptr(attrs);
+	ctx->tm = tm;
+	return &no_free_ptr(ctx)->agrp;
+}
+EXPORT_SYMBOL_GPL(tsm_mr_create_attribute_group);
+
+/**
+ * tsm_mr_free_attribute_group() - frees the attribute group returned by
+ * tsm_mr_create_attribute_group()
+ * @attr_grp: attribute group returned by tsm_mr_create_attribute_group()
+ *
+ * Context: Process context.
+ */
+void tsm_mr_free_attribute_group(const struct attribute_group *attr_grp)
+{
+	if (!IS_ERR_OR_NULL(attr_grp)) {
+		kfree(attr_grp->bin_attrs);
+		kfree(container_of(attr_grp, struct tm_context, agrp));
+	}
+}
+EXPORT_SYMBOL_GPL(tsm_mr_free_attribute_group);

linux-7.2.3/drivers/virt/coco/pkvm-guest/Kconfig

@@ -0,0 +1,10 @@
+config ARM_PKVM_GUEST
+	bool "Arm pKVM protected guest driver"
+	depends on ARM64 && DMA_RESTRICTED_POOL
+	help
+	  Protected guests running under the pKVM hypervisor on arm64
+	  are isolated from the host and must issue hypercalls to enable
+	  interaction with virtual devices. This driver implements
+	  support for probing and issuing these hypercalls.
+
+	  If unsure, say 'N'.

linux-7.2.3/drivers/virt/coco/pkvm-guest/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_ARM_PKVM_GUEST) += arm-pkvm-guest.o

linux-7.2.3/drivers/virt/coco/pkvm-guest/arm-pkvm-guest.c

@@ -0,0 +1,123 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Support for the hypercall interface exposed to protected guests by
+ * pKVM.
+ *
+ * Author: Will Deacon <will@kernel.org>
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include <linux/arm-smccc.h>
+#include <linux/array_size.h>
+#include <linux/io.h>
+#include <linux/mem_encrypt.h>
+#include <linux/mm.h>
+#include <linux/pgtable.h>
+
+#include <asm/hypervisor.h>
+
+static size_t pkvm_granule;
+
+static int arm_smccc_do_one_page(u32 func_id, phys_addr_t phys)
+{
+	phys_addr_t end = phys + PAGE_SIZE;
+
+	while (phys < end) {
+		struct arm_smccc_res res;
+
+		arm_smccc_1_1_invoke(func_id, phys, 0, 0, &res);
+		if (res.a0 != SMCCC_RET_SUCCESS)
+			return -EPERM;
+
+		phys += pkvm_granule;
+	}
+
+	return 0;
+}
+
+static int __set_memory_range(u32 func_id, unsigned long start, int numpages)
+{
+	void *addr = (void *)start, *end = addr + numpages * PAGE_SIZE;
+
+	while (addr < end) {
+		int err;
+
+		err = arm_smccc_do_one_page(func_id, virt_to_phys(addr));
+		if (err)
+			return err;
+
+		addr += PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+static int pkvm_set_memory_encrypted(unsigned long addr, int numpages)
+{
+	return __set_memory_range(ARM_SMCCC_VENDOR_HYP_KVM_MEM_UNSHARE_FUNC_ID,
+				  addr, numpages);
+}
+
+static int pkvm_set_memory_decrypted(unsigned long addr, int numpages)
+{
+	return __set_memory_range(ARM_SMCCC_VENDOR_HYP_KVM_MEM_SHARE_FUNC_ID,
+				  addr, numpages);
+}
+
+static const struct arm64_mem_crypt_ops pkvm_crypt_ops = {
+	.encrypt	= pkvm_set_memory_encrypted,
+	.decrypt	= pkvm_set_memory_decrypted,
+};
+
+static int mmio_guard_ioremap_hook(phys_addr_t phys, size_t size,
+				   pgprot_t *prot)
+{
+	phys_addr_t end;
+	pteval_t protval = pgprot_val(*prot);
+
+	/*
+	 * We only expect MMIO emulation for regions mapped with device
+	 * attributes.
+	 */
+	if (protval != PROT_DEVICE_nGnRE && protval != PROT_DEVICE_nGnRnE)
+		return 0;
+
+	end = PAGE_ALIGN(phys + size);
+	phys = PAGE_ALIGN_DOWN(phys);
+
+	while (phys < end) {
+		const int func_id = ARM_SMCCC_VENDOR_HYP_KVM_MMIO_GUARD_FUNC_ID;
+
+		WARN_ON_ONCE(arm_smccc_do_one_page(func_id, phys));
+		phys += PAGE_SIZE;
+	}
+
+	return 0;
+}
+
+void pkvm_init_hyp_services(void)
+{
+	int i;
+	struct arm_smccc_res res;
+	const u32 funcs[] = {
+		ARM_SMCCC_KVM_FUNC_HYP_MEMINFO,
+		ARM_SMCCC_KVM_FUNC_MEM_SHARE,
+		ARM_SMCCC_KVM_FUNC_MEM_UNSHARE,
+	};
+
+	for (i = 0; i < ARRAY_SIZE(funcs); ++i) {
+		if (!kvm_arm_hyp_service_available(funcs[i]))
+			return;
+	}
+
+	arm_smccc_1_1_invoke(ARM_SMCCC_VENDOR_HYP_KVM_HYP_MEMINFO_FUNC_ID,
+			     0, 0, 0, &res);
+	if (res.a0 > PAGE_SIZE) /* Includes error codes */
+		return;
+
+	pkvm_granule = res.a0;
+	arm64_mem_crypt_ops_register(&pkvm_crypt_ops);
+
+	if (kvm_arm_hyp_service_available(ARM_SMCCC_KVM_FUNC_MMIO_GUARD))
+		arm64_ioremap_prot_hook_register(&mmio_guard_ioremap_hook);
+}

linux-7.2.3/drivers/virt/coco/sev-guest/Kconfig

@@ -0,0 +1,13 @@
+config SEV_GUEST
+	tristate "AMD SEV Guest driver"
+	default m
+	depends on AMD_MEM_ENCRYPT
+	select TSM_REPORTS
+	help
+	  SEV-SNP firmware provides the guest a mechanism to communicate with
+	  the PSP without risk from a malicious hypervisor who wishes to read,
+	  alter, drop or replay the messages sent. The driver provides
+	  userspace interface to communicate with the PSP to request the
+	  attestation report and more.
+
+	  If you choose 'M' here, this module will be called sev-guest.

linux-7.2.3/drivers/virt/coco/sev-guest/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_SEV_GUEST) += sev-guest.o

linux-7.2.3/drivers/virt/coco/sev-guest/sev-guest.c

@@ -0,0 +1,717 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Secure Encrypted Virtualization (SEV) guest driver interface
+ *
+ * Copyright (C) 2021-2024 Advanced Micro Devices, Inc.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/miscdevice.h>
+#include <linux/set_memory.h>
+#include <linux/fs.h>
+#include <linux/tsm.h>
+#include <crypto/gcm.h>
+#include <linux/psp-sev.h>
+#include <linux/sockptr.h>
+#include <linux/cleanup.h>
+#include <linux/uuid.h>
+#include <linux/configfs.h>
+#include <linux/mm.h>
+#include <uapi/linux/sev-guest.h>
+#include <uapi/linux/psp-sev.h>
+
+#include <asm/svm.h>
+#include <asm/sev.h>
+
+#define DEVICE_NAME	"sev-guest"
+
+#define SVSM_MAX_RETRIES		3
+
+struct snp_guest_dev {
+	struct device *dev;
+	struct miscdevice misc;
+
+	struct snp_msg_desc *msg_desc;
+};
+
+/*
+ * The VMPCK ID represents the key used by the SNP guest to communicate with the
+ * SEV firmware in the AMD Secure Processor (ASP, aka PSP). By default, the key
+ * used will be the key associated with the VMPL at which the guest is running.
+ * Should the default key be wiped (see snp_disable_vmpck()), this parameter
+ * allows for using one of the remaining VMPCKs.
+ */
+static int vmpck_id = -1;
+module_param(vmpck_id, int, 0444);
+MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP.");
+
+static inline struct snp_guest_dev *to_snp_dev(struct file *file)
+{
+	struct miscdevice *dev = file->private_data;
+
+	return container_of(dev, struct snp_guest_dev, misc);
+}
+
+struct snp_req_resp {
+	sockptr_t req_data;
+	sockptr_t resp_data;
+};
+
+static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
+{
+	struct snp_report_req *report_req __free(kfree) = NULL;
+	struct snp_msg_desc *mdesc = snp_dev->msg_desc;
+	struct snp_report_resp *report_resp;
+	struct snp_guest_req req = {};
+	int rc, resp_len;
+
+	if (!arg->req_data || !arg->resp_data)
+		return -EINVAL;
+
+	report_req = kzalloc_obj(*report_req, GFP_KERNEL_ACCOUNT);
+	if (!report_req)
+		return -ENOMEM;
+
+	if (copy_from_user(report_req, (void __user *)arg->req_data, sizeof(*report_req)))
+		return -EFAULT;
+
+	/*
+	 * The intermediate response buffer is used while decrypting the
+	 * response payload. Make sure that it has enough space to cover the
+	 * authtag.
+	 */
+	resp_len = sizeof(report_resp->data) + mdesc->ctx->authsize;
+	report_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT);
+	if (!report_resp)
+		return -ENOMEM;
+
+	req.msg_version = arg->msg_version;
+	req.msg_type = SNP_MSG_REPORT_REQ;
+	req.vmpck_id = mdesc->vmpck_id;
+	req.req_buf = report_req;
+	req.req_sz = sizeof(*report_req);
+	req.resp_buf = report_resp->data;
+	req.resp_sz = resp_len;
+	req.exit_code = SVM_VMGEXIT_GUEST_REQUEST;
+
+	rc = snp_send_guest_request(mdesc, &req);
+	arg->exitinfo2 = req.exitinfo2;
+	if (rc)
+		goto e_free;
+
+	if (copy_to_user((void __user *)arg->resp_data, report_resp, sizeof(*report_resp)))
+		rc = -EFAULT;
+
+e_free:
+	kfree(report_resp);
+	return rc;
+}
+
+static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
+{
+	struct snp_derived_key_resp *derived_key_resp __free(kfree) = NULL;
+	struct snp_derived_key_req *derived_key_req __free(kfree) = NULL;
+	struct snp_msg_desc *mdesc = snp_dev->msg_desc;
+	struct snp_guest_req req = {};
+	int rc, resp_len;
+
+	if (!arg->req_data || !arg->resp_data)
+		return -EINVAL;
+
+	/*
+	 * The intermediate response buffer is used while decrypting the
+	 * response payload. Make sure that it has enough space to cover the
+	 * authtag.
+	 */
+	resp_len = sizeof(derived_key_resp->data) + mdesc->ctx->authsize;
+	derived_key_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT);
+	if (!derived_key_resp)
+		return -ENOMEM;
+
+	derived_key_req = kzalloc_obj(*derived_key_req, GFP_KERNEL_ACCOUNT);
+	if (!derived_key_req)
+		return -ENOMEM;
+
+	if (copy_from_user(derived_key_req, (void __user *)arg->req_data,
+			   sizeof(*derived_key_req)))
+		return -EFAULT;
+
+	req.msg_version = arg->msg_version;
+	req.msg_type = SNP_MSG_KEY_REQ;
+	req.vmpck_id = mdesc->vmpck_id;
+	req.req_buf = derived_key_req;
+	req.req_sz = sizeof(*derived_key_req);
+	req.resp_buf = derived_key_resp;
+	req.resp_sz = resp_len;
+	req.exit_code = SVM_VMGEXIT_GUEST_REQUEST;
+
+	rc = snp_send_guest_request(mdesc, &req);
+	arg->exitinfo2 = req.exitinfo2;
+	if (!rc) {
+		if (copy_to_user((void __user *)arg->resp_data, derived_key_resp,
+				 sizeof(derived_key_resp->data)))
+			rc = -EFAULT;
+	}
+
+	/* The response buffer contains the sensitive data, explicitly clear it. */
+	memzero_explicit(derived_key_resp, sizeof(*derived_key_resp));
+
+	return rc;
+}
+
+static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg,
+			  struct snp_req_resp *io)
+
+{
+	struct snp_ext_report_req *report_req __free(kfree) = NULL;
+	struct snp_msg_desc *mdesc = snp_dev->msg_desc;
+	struct snp_report_resp *report_resp;
+	struct snp_guest_req req = {};
+	int ret, npages = 0, resp_len;
+	sockptr_t certs_address;
+	u64 pfn;
+
+	if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data))
+		return -EINVAL;
+
+	report_req = kzalloc_obj(*report_req, GFP_KERNEL_ACCOUNT);
+	if (!report_req)
+		return -ENOMEM;
+
+	if (copy_from_sockptr(report_req, io->req_data, sizeof(*report_req)))
+		return -EFAULT;
+
+	/* caller does not want certificate data */
+	if (!report_req->certs_len || !report_req->certs_address)
+		goto cmd;
+
+	if (report_req->certs_len > SEV_FW_BLOB_MAX_SIZE ||
+	    !IS_ALIGNED(report_req->certs_len, PAGE_SIZE))
+		return -EINVAL;
+
+	if (sockptr_is_kernel(io->resp_data)) {
+		certs_address = KERNEL_SOCKPTR((void *)report_req->certs_address);
+	} else {
+		certs_address = USER_SOCKPTR((void __user *)report_req->certs_address);
+		if (!access_ok(certs_address.user, report_req->certs_len))
+			return -EFAULT;
+	}
+
+	/*
+	 * Initialize the intermediate buffer with all zeros. This buffer
+	 * is used in the guest request message to get the certs blob from
+	 * the host. If host does not supply any certs in it, then copy
+	 * zeros to indicate that certificate data was not provided.
+	 */
+	npages = report_req->certs_len >> PAGE_SHIFT;
+	req.certs_data = alloc_pages_exact(npages << PAGE_SHIFT,
+					   GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+	if (!req.certs_data)
+		return -ENOMEM;
+
+	pfn = PHYS_PFN(virt_to_phys(req.certs_data));
+	ret = set_memory_decrypted((unsigned long)req.certs_data, npages);
+	if (ret) {
+		pr_err("failed to mark page shared, ret=%d\n", ret);
+		snp_leak_pages(pfn, npages);
+		return -EFAULT;
+	}
+
+cmd:
+	/*
+	 * The intermediate response buffer is used while decrypting the
+	 * response payload. Make sure that it has enough space to cover the
+	 * authtag.
+	 */
+	resp_len = sizeof(report_resp->data) + mdesc->ctx->authsize;
+	report_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT);
+	if (!report_resp) {
+		ret = -ENOMEM;
+		goto e_free_data;
+	}
+
+	req.input.data_npages = npages;
+
+	req.msg_version = arg->msg_version;
+	req.msg_type = SNP_MSG_REPORT_REQ;
+	req.vmpck_id = mdesc->vmpck_id;
+	req.req_buf = &report_req->data;
+	req.req_sz = sizeof(report_req->data);
+	req.resp_buf = report_resp->data;
+	req.resp_sz = resp_len;
+	req.exit_code = SVM_VMGEXIT_EXT_GUEST_REQUEST;
+
+	ret = snp_send_guest_request(mdesc, &req);
+	arg->exitinfo2 = req.exitinfo2;
+
+	/* If certs length is invalid then copy the returned length */
+	if (arg->vmm_error == SNP_GUEST_VMM_ERR_INVALID_LEN) {
+		report_req->certs_len = req.input.data_npages << PAGE_SHIFT;
+
+		if (copy_to_sockptr(io->req_data, report_req, sizeof(*report_req)))
+			ret = -EFAULT;
+	}
+
+	if (ret)
+		goto e_free;
+
+	if (npages && copy_to_sockptr(certs_address, req.certs_data, report_req->certs_len)) {
+		ret = -EFAULT;
+		goto e_free;
+	}
+
+	if (copy_to_sockptr(io->resp_data, report_resp, sizeof(*report_resp)))
+		ret = -EFAULT;
+
+e_free:
+	kfree(report_resp);
+e_free_data:
+	if (npages) {
+		if (set_memory_encrypted((unsigned long)req.certs_data, npages)) {
+			WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n");
+			snp_leak_pages(pfn, npages);
+		} else {
+			free_pages_exact(req.certs_data, npages << PAGE_SHIFT);
+		}
+	}
+	return ret;
+}
+
+static long snp_guest_ioctl(struct file *file, unsigned int ioctl, unsigned long arg)
+{
+	struct snp_guest_dev *snp_dev = to_snp_dev(file);
+	void __user *argp = (void __user *)arg;
+	struct snp_guest_request_ioctl input;
+	struct snp_req_resp io;
+	int ret = -ENOTTY;
+
+	if (copy_from_user(&input, argp, sizeof(input)))
+		return -EFAULT;
+
+	input.exitinfo2 = 0xff;
+
+	/* Message version must be non-zero */
+	if (!input.msg_version)
+		return -EINVAL;
+
+	switch (ioctl) {
+	case SNP_GET_REPORT:
+		ret = get_report(snp_dev, &input);
+		break;
+	case SNP_GET_DERIVED_KEY:
+		ret = get_derived_key(snp_dev, &input);
+		break;
+	case SNP_GET_EXT_REPORT:
+		/*
+		 * As get_ext_report() may be called from the ioctl() path and a
+		 * kernel internal path (configfs-tsm), decorate the passed
+		 * buffers as user pointers.
+		 */
+		io.req_data = USER_SOCKPTR((void __user *)input.req_data);
+		io.resp_data = USER_SOCKPTR((void __user *)input.resp_data);
+		ret = get_ext_report(snp_dev, &input, &io);
+		break;
+	default:
+		break;
+	}
+
+	if (input.exitinfo2 && copy_to_user(argp, &input, sizeof(input)))
+		return -EFAULT;
+
+	return ret;
+}
+
+static const struct file_operations snp_guest_fops = {
+	.owner	= THIS_MODULE,
+	.unlocked_ioctl = snp_guest_ioctl,
+};
+
+struct snp_msg_report_resp_hdr {
+	u32 status;
+	u32 report_size;
+	u8 rsvd[24];
+};
+
+struct snp_msg_cert_entry {
+	guid_t guid;
+	u32 offset;
+	u32 length;
+};
+
+static int sev_svsm_report_new(struct tsm_report *report, void *data)
+{
+	unsigned int rep_len, man_len, certs_len;
+	struct tsm_report_desc *desc = &report->desc;
+	struct svsm_attest_call ac = {};
+	unsigned int retry_count;
+	void *rep, *man, *certs;
+	struct svsm_call call;
+	unsigned int size;
+	bool try_again;
+	void *buffer;
+	u64 call_id;
+	int ret;
+
+	/*
+	 * Allocate pages for the request:
+	 * - Report blob (4K)
+	 * - Manifest blob (4K)
+	 * - Certificate blob (16K)
+	 *
+	 * Above addresses must be 4K aligned
+	 */
+	rep_len = SZ_4K;
+	man_len = SZ_4K;
+	certs_len = SEV_FW_BLOB_MAX_SIZE;
+
+	if (guid_is_null(&desc->service_guid)) {
+		call_id = SVSM_ATTEST_CALL(SVSM_ATTEST_SERVICES);
+	} else {
+		export_guid(ac.service_guid, &desc->service_guid);
+		ac.service_manifest_ver = desc->service_manifest_version;
+
+		call_id = SVSM_ATTEST_CALL(SVSM_ATTEST_SINGLE_SERVICE);
+	}
+
+	retry_count = 0;
+
+retry:
+	memset(&call, 0, sizeof(call));
+
+	size = rep_len + man_len + certs_len;
+	buffer = alloc_pages_exact(size, __GFP_ZERO);
+	if (!buffer)
+		return -ENOMEM;
+
+	rep = buffer;
+	ac.report_buf.pa = __pa(rep);
+	ac.report_buf.len = rep_len;
+
+	man = rep + rep_len;
+	ac.manifest_buf.pa = __pa(man);
+	ac.manifest_buf.len = man_len;
+
+	certs = man + man_len;
+	ac.certificates_buf.pa = __pa(certs);
+	ac.certificates_buf.len = certs_len;
+
+	ac.nonce.pa = __pa(desc->inblob);
+	ac.nonce.len = desc->inblob_len;
+
+	ret = snp_issue_svsm_attest_req(call_id, &call, &ac);
+	if (ret) {
+		free_pages_exact(buffer, size);
+
+		switch (call.rax_out) {
+		case SVSM_ERR_INVALID_PARAMETER:
+			try_again = false;
+
+			if (ac.report_buf.len > rep_len) {
+				rep_len = PAGE_ALIGN(ac.report_buf.len);
+				try_again = true;
+			}
+
+			if (ac.manifest_buf.len > man_len) {
+				man_len = PAGE_ALIGN(ac.manifest_buf.len);
+				try_again = true;
+			}
+
+			if (ac.certificates_buf.len > certs_len) {
+				certs_len = PAGE_ALIGN(ac.certificates_buf.len);
+				try_again = true;
+			}
+
+			/* If one of the buffers wasn't large enough, retry the request */
+			if (try_again && retry_count < SVSM_MAX_RETRIES) {
+				retry_count++;
+				goto retry;
+			}
+
+			return -EINVAL;
+		default:
+			pr_err_ratelimited("SVSM attestation request failed (%d / 0x%llx)\n",
+					   ret, call.rax_out);
+			return -EINVAL;
+		}
+	}
+
+	/*
+	 * Allocate all the blob memory buffers at once so that the cleanup is
+	 * done for errors that occur after the first allocation (i.e. before
+	 * using no_free_ptr()).
+	 */
+	rep_len = ac.report_buf.len;
+	void *rbuf __free(kvfree) = kvzalloc(rep_len, GFP_KERNEL);
+
+	man_len = ac.manifest_buf.len;
+	void *mbuf __free(kvfree) = kvzalloc(man_len, GFP_KERNEL);
+
+	certs_len = ac.certificates_buf.len;
+	void *cbuf __free(kvfree) = certs_len ? kvzalloc(certs_len, GFP_KERNEL) : NULL;
+
+	if (!rbuf || !mbuf || (certs_len && !cbuf)) {
+		free_pages_exact(buffer, size);
+		return -ENOMEM;
+	}
+
+	memcpy(rbuf, rep, rep_len);
+	report->outblob = no_free_ptr(rbuf);
+	report->outblob_len = rep_len;
+
+	memcpy(mbuf, man, man_len);
+	report->manifestblob = no_free_ptr(mbuf);
+	report->manifestblob_len = man_len;
+
+	if (certs_len) {
+		memcpy(cbuf, certs, certs_len);
+		report->auxblob = no_free_ptr(cbuf);
+		report->auxblob_len = certs_len;
+	}
+
+	free_pages_exact(buffer, size);
+
+	return 0;
+}
+
+static int sev_report_new(struct tsm_report *report, void *data)
+{
+	struct snp_msg_cert_entry *cert_table;
+	struct tsm_report_desc *desc = &report->desc;
+	struct snp_guest_dev *snp_dev = data;
+	struct snp_msg_report_resp_hdr hdr;
+	const u32 report_size = SZ_4K;
+	const u32 ext_size = SEV_FW_BLOB_MAX_SIZE;
+	u32 certs_size, i, size = report_size + ext_size;
+	int ret;
+
+	if (desc->inblob_len != SNP_REPORT_USER_DATA_SIZE)
+		return -EINVAL;
+
+	if (desc->service_provider) {
+		if (strcmp(desc->service_provider, "svsm"))
+			return -EINVAL;
+
+		return sev_svsm_report_new(report, data);
+	}
+
+	void *buf __free(kvfree) = kvzalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	cert_table = buf + report_size;
+	struct snp_ext_report_req ext_req = {
+		.data = { .vmpl = desc->privlevel },
+		.certs_address = (__u64)cert_table,
+		.certs_len = ext_size,
+	};
+	memcpy(&ext_req.data.user_data, desc->inblob, desc->inblob_len);
+
+	struct snp_guest_request_ioctl input = {
+		.msg_version = 1,
+		.req_data = (__u64)&ext_req,
+		.resp_data = (__u64)buf,
+		.exitinfo2 = 0xff,
+	};
+	struct snp_req_resp io = {
+		.req_data = KERNEL_SOCKPTR(&ext_req),
+		.resp_data = KERNEL_SOCKPTR(buf),
+	};
+
+	ret = get_ext_report(snp_dev, &input, &io);
+	if (ret)
+		return ret;
+
+	memcpy(&hdr, buf, sizeof(hdr));
+	if (hdr.status == SEV_RET_INVALID_PARAM)
+		return -EINVAL;
+	if (hdr.status == SEV_RET_INVALID_KEY)
+		return -EINVAL;
+	if (hdr.status)
+		return -ENXIO;
+	if ((hdr.report_size + sizeof(hdr)) > report_size)
+		return -ENOMEM;
+
+	void *rbuf __free(kvfree) = kvzalloc(hdr.report_size, GFP_KERNEL);
+	if (!rbuf)
+		return -ENOMEM;
+
+	memcpy(rbuf, buf + sizeof(hdr), hdr.report_size);
+	report->outblob = no_free_ptr(rbuf);
+	report->outblob_len = hdr.report_size;
+
+	certs_size = 0;
+	for (i = 0; i < ext_size / sizeof(struct snp_msg_cert_entry); i++) {
+		struct snp_msg_cert_entry *ent = &cert_table[i];
+
+		if (guid_is_null(&ent->guid) && !ent->offset && !ent->length)
+			break;
+		certs_size = max(certs_size, ent->offset + ent->length);
+	}
+
+	/* Suspicious that the response populated entries without populating size */
+	if (!certs_size && i)
+		dev_warn_ratelimited(snp_dev->dev, "certificate slots conveyed without size\n");
+
+	/* No certs to report */
+	if (!certs_size)
+		return 0;
+
+	/* Suspicious that the certificate blob size contract was violated
+	 */
+	if (certs_size > ext_size) {
+		dev_warn_ratelimited(snp_dev->dev, "certificate data truncated\n");
+		certs_size = ext_size;
+	}
+
+	void *cbuf __free(kvfree) = kvzalloc(certs_size, GFP_KERNEL);
+	if (!cbuf)
+		return -ENOMEM;
+
+	memcpy(cbuf, cert_table, certs_size);
+	report->auxblob = no_free_ptr(cbuf);
+	report->auxblob_len = certs_size;
+
+	return 0;
+}
+
+static bool sev_report_attr_visible(int n)
+{
+	switch (n) {
+	case TSM_REPORT_GENERATION:
+	case TSM_REPORT_PROVIDER:
+	case TSM_REPORT_PRIVLEVEL:
+	case TSM_REPORT_PRIVLEVEL_FLOOR:
+		return true;
+	case TSM_REPORT_SERVICE_PROVIDER:
+	case TSM_REPORT_SERVICE_GUID:
+	case TSM_REPORT_SERVICE_MANIFEST_VER:
+		return snp_vmpl;
+	}
+
+	return false;
+}
+
+static bool sev_report_bin_attr_visible(int n)
+{
+	switch (n) {
+	case TSM_REPORT_INBLOB:
+	case TSM_REPORT_OUTBLOB:
+	case TSM_REPORT_AUXBLOB:
+		return true;
+	case TSM_REPORT_MANIFESTBLOB:
+		return snp_vmpl;
+	}
+
+	return false;
+}
+
+static struct tsm_report_ops sev_tsm_report_ops = {
+	.name = KBUILD_MODNAME,
+	.report_new = sev_report_new,
+	.report_attr_visible = sev_report_attr_visible,
+	.report_bin_attr_visible = sev_report_bin_attr_visible,
+};
+
+static void unregister_sev_tsm(void *data)
+{
+	tsm_report_unregister(&sev_tsm_report_ops);
+}
+
+static int __init sev_guest_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct snp_guest_dev *snp_dev;
+	struct snp_msg_desc *mdesc;
+	struct miscdevice *misc;
+	int ret;
+
+	BUILD_BUG_ON(sizeof(struct snp_guest_msg) > PAGE_SIZE);
+
+	if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+		return -ENODEV;
+
+	snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL);
+	if (!snp_dev)
+		return -ENOMEM;
+
+	mdesc = snp_msg_alloc();
+	if (IS_ERR_OR_NULL(mdesc))
+		return -ENOMEM;
+
+	ret = snp_msg_init(mdesc, vmpck_id);
+	if (ret)
+		goto e_msg_init;
+
+	platform_set_drvdata(pdev, snp_dev);
+	snp_dev->dev = dev;
+
+	misc = &snp_dev->misc;
+	misc->minor = MISC_DYNAMIC_MINOR;
+	misc->name = DEVICE_NAME;
+	misc->fops = &snp_guest_fops;
+
+	/* Set the privlevel_floor attribute based on the vmpck_id */
+	sev_tsm_report_ops.privlevel_floor = mdesc->vmpck_id;
+
+	ret = tsm_report_register(&sev_tsm_report_ops, snp_dev);
+	if (ret)
+		goto e_msg_init;
+
+	ret = devm_add_action_or_reset(&pdev->dev, unregister_sev_tsm, NULL);
+	if (ret)
+		goto e_msg_init;
+
+	ret =  misc_register(misc);
+	if (ret)
+		goto e_msg_init;
+
+	snp_dev->msg_desc = mdesc;
+	dev_info(dev, "Initialized SEV guest driver (using VMPCK%d communication key)\n",
+		 mdesc->vmpck_id);
+	return 0;
+
+e_msg_init:
+	snp_msg_free(mdesc);
+
+	return ret;
+}
+
+static void __exit sev_guest_remove(struct platform_device *pdev)
+{
+	struct snp_guest_dev *snp_dev = platform_get_drvdata(pdev);
+
+	snp_msg_free(snp_dev->msg_desc);
+	misc_deregister(&snp_dev->misc);
+}
+
+/*
+ * This driver is meant to be a common SEV guest interface driver and to
+ * support any SEV guest API. As such, even though it has been introduced
+ * with the SEV-SNP support, it is named "sev-guest".
+ *
+ * sev_guest_remove() lives in .exit.text. For drivers registered via
+ * module_platform_driver_probe() this is ok because they cannot get unbound
+ * at runtime. So mark the driver struct with __refdata to prevent modpost
+ * triggering a section mismatch warning.
+ */
+static struct platform_driver sev_guest_driver __refdata = {
+	.remove		= __exit_p(sev_guest_remove),
+	.driver		= {
+		.name = "sev-guest",
+	},
+};
+
+module_platform_driver_probe(sev_guest_driver, sev_guest_probe);
+
+MODULE_AUTHOR("Brijesh Singh <brijesh.singh@amd.com>");
+MODULE_LICENSE("GPL");
+MODULE_VERSION("1.0.0");
+MODULE_DESCRIPTION("AMD SEV Guest Driver");
+MODULE_ALIAS("platform:sev-guest");

linux-7.2.3/drivers/virt/coco/tdx-guest/Kconfig

@@ -0,0 +1,12 @@
+config TDX_GUEST_DRIVER
+	tristate "TDX Guest driver"
+	depends on INTEL_TDX_GUEST
+	select TSM_REPORTS
+	select TSM_MEASUREMENTS
+	help
+	  The driver provides userspace interface to communicate with
+	  the TDX module to request the TDX guest details like attestation
+	  report.
+
+	  To compile this driver as module, choose M here. The module will
+	  be called tdx-guest.

linux-7.2.3/drivers/virt/coco/tdx-guest/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_TDX_GUEST_DRIVER) += tdx-guest.o

linux-7.2.3/drivers/virt/coco/tdx-guest/tdx-guest.c

@@ -0,0 +1,455 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * TDX guest user interface driver
+ *
+ * Copyright (C) 2022 Intel Corporation
+ */
+
+#define pr_fmt(fmt)			KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/set_memory.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/sockptr.h>
+#include <linux/tsm.h>
+#include <linux/tsm-mr.h>
+
+#include <uapi/linux/tdx-guest.h>
+
+#include <asm/cpu_device_id.h>
+#include <asm/tdx.h>
+
+/* TDREPORT buffer */
+static u8 *tdx_report_buf;
+
+/* Lock to serialize TDG.MR.REPORT and TDG.MR.RTMR.EXTEND TDCALLs */
+static DEFINE_MUTEX(mr_lock);
+
+/* TDREPORT fields */
+enum {
+	TDREPORT_reportdata = 128,
+	TDREPORT_tee_tcb_info = 256,
+	TDREPORT_tdinfo = TDREPORT_tee_tcb_info + 256,
+	TDREPORT_attributes = TDREPORT_tdinfo,
+	TDREPORT_xfam = TDREPORT_attributes + sizeof(u64),
+	TDREPORT_mrtd = TDREPORT_xfam + sizeof(u64),
+	TDREPORT_mrconfigid = TDREPORT_mrtd + SHA384_DIGEST_SIZE,
+	TDREPORT_mrowner = TDREPORT_mrconfigid + SHA384_DIGEST_SIZE,
+	TDREPORT_mrownerconfig = TDREPORT_mrowner + SHA384_DIGEST_SIZE,
+	TDREPORT_rtmr0 = TDREPORT_mrownerconfig + SHA384_DIGEST_SIZE,
+	TDREPORT_rtmr1 = TDREPORT_rtmr0 + SHA384_DIGEST_SIZE,
+	TDREPORT_rtmr2 = TDREPORT_rtmr1 + SHA384_DIGEST_SIZE,
+	TDREPORT_rtmr3 = TDREPORT_rtmr2 + SHA384_DIGEST_SIZE,
+	TDREPORT_servtd_hash = TDREPORT_rtmr3 + SHA384_DIGEST_SIZE,
+};
+
+static int tdx_do_report(sockptr_t data, sockptr_t tdreport)
+{
+	scoped_cond_guard(mutex_intr, return -EINTR, &mr_lock) {
+		u8 *reportdata = tdx_report_buf + TDREPORT_reportdata;
+		int ret;
+
+		if (!sockptr_is_null(data) &&
+		    copy_from_sockptr(reportdata, data, TDX_REPORTDATA_LEN))
+			return -EFAULT;
+
+		ret = tdx_mcall_get_report0(reportdata, tdx_report_buf);
+		if (WARN_ONCE(ret, "tdx_mcall_get_report0() failed: %d", ret))
+			return ret;
+
+		if (!sockptr_is_null(tdreport) &&
+		    copy_to_sockptr(tdreport, tdx_report_buf, TDX_REPORT_LEN))
+			return -EFAULT;
+	}
+	return 0;
+}
+
+static int tdx_do_extend(u8 mr_ind, const u8 *data)
+{
+	scoped_cond_guard(mutex_intr, return -EINTR, &mr_lock) {
+		/*
+		 * TDX requires @extend_buf to be 64-byte aligned.
+		 * It's safe to use REPORTDATA buffer for that purpose because
+		 * tdx_mr_report/extend_lock() are mutually exclusive.
+		 */
+		u8 *extend_buf = tdx_report_buf + TDREPORT_reportdata;
+		int ret;
+
+		memcpy(extend_buf, data, SHA384_DIGEST_SIZE);
+
+		ret = tdx_mcall_extend_rtmr(mr_ind, extend_buf);
+		if (WARN_ONCE(ret, "tdx_mcall_extend_rtmr(%u) failed: %d", mr_ind, ret))
+			return ret;
+	}
+	return 0;
+}
+
+#define TDX_MR_(r) .mr_value = (void *)TDREPORT_##r, TSM_MR_(r, SHA384)
+static struct tsm_measurement_register tdx_mrs[] = {
+	{ TDX_MR_(rtmr0) | TSM_MR_F_RTMR },
+	{ TDX_MR_(rtmr1) | TSM_MR_F_RTMR },
+	{ TDX_MR_(rtmr2) | TSM_MR_F_RTMR },
+	{ TDX_MR_(rtmr3) | TSM_MR_F_RTMR },
+	{ TDX_MR_(mrtd) },
+	{ TDX_MR_(mrconfigid) | TSM_MR_F_NOHASH },
+	{ TDX_MR_(mrowner) | TSM_MR_F_NOHASH },
+	{ TDX_MR_(mrownerconfig) | TSM_MR_F_NOHASH },
+};
+#undef TDX_MR_
+
+static int tdx_mr_refresh(const struct tsm_measurements *tm)
+{
+	return tdx_do_report(KERNEL_SOCKPTR(NULL), KERNEL_SOCKPTR(NULL));
+}
+
+static int tdx_mr_extend(const struct tsm_measurements *tm,
+			 const struct tsm_measurement_register *mr,
+			 const u8 *data)
+{
+	return tdx_do_extend(mr - tm->mrs, data);
+}
+
+static struct tsm_measurements tdx_measurements = {
+	.mrs = tdx_mrs,
+	.nr_mrs = ARRAY_SIZE(tdx_mrs),
+	.refresh = tdx_mr_refresh,
+	.write = tdx_mr_extend,
+};
+
+static const struct attribute_group *tdx_mr_init(void)
+{
+	const struct attribute_group *g;
+	int rc;
+
+	u8 *buf __free(kfree) = kzalloc(TDX_REPORT_LEN, GFP_KERNEL);
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+
+	tdx_report_buf = buf;
+	rc = tdx_mr_refresh(&tdx_measurements);
+	if (rc)
+		return ERR_PTR(rc);
+
+	/*
+	 * @mr_value was initialized with the offset only, while the base
+	 * address is being added here.
+	 */
+	for (size_t i = 0; i < ARRAY_SIZE(tdx_mrs); ++i)
+		*(long *)&tdx_mrs[i].mr_value += (long)buf;
+
+	g = tsm_mr_create_attribute_group(&tdx_measurements);
+	if (!IS_ERR(g))
+		tdx_report_buf = no_free_ptr(buf);
+
+	return g;
+}
+
+static void tdx_mr_deinit(const struct attribute_group *mr_grp)
+{
+	tsm_mr_free_attribute_group(mr_grp);
+	kfree(tdx_report_buf);
+}
+
+/*
+ * Intel's SGX QE implementation generally uses Quote size less
+ * than 8K (2K Quote data + ~5K of certificate blob).
+ * DICE-based attestation uses layered evidence that requires
+ * larger Quote size (~100K).
+ */
+#define GET_QUOTE_BUF_SIZE		SZ_128K
+
+#define GET_QUOTE_CMD_VER		1
+
+/* TDX GetQuote status codes */
+#define GET_QUOTE_SUCCESS		0
+#define GET_QUOTE_IN_FLIGHT		0xffffffffffffffff
+
+#define TDX_QUOTE_MAX_LEN		(GET_QUOTE_BUF_SIZE - sizeof(struct tdx_quote_buf))
+
+/* struct tdx_quote_buf: Format of Quote request buffer.
+ * @version: Quote format version, filled by TD.
+ * @status: Status code of Quote request, filled by VMM.
+ * @in_len: Length of TDREPORT, filled by TD.
+ * @out_len: Length of Quote data, filled by VMM.
+ * @data: Quote data on output or TDREPORT on input.
+ *
+ * More details of Quote request buffer can be found in TDX
+ * Guest-Host Communication Interface (GHCI) for Intel TDX 1.0,
+ * section titled "TDG.VP.VMCALL<GetQuote>"
+ */
+struct tdx_quote_buf {
+	u64 version;
+	u64 status;
+	u32 in_len;
+	u32 out_len;
+	u8 data[];
+};
+
+/* Quote data buffer */
+static void *quote_data;
+
+/* Lock to streamline quote requests */
+static DEFINE_MUTEX(quote_lock);
+
+/*
+ * GetQuote request timeout in seconds. Expect that 30 seconds
+ * is enough time for QE to respond to any Quote requests.
+ */
+static u32 getquote_timeout = 30;
+
+static long tdx_get_report0(struct tdx_report_req __user *req)
+{
+	return tdx_do_report(USER_SOCKPTR(req->reportdata),
+			     USER_SOCKPTR(req->tdreport));
+}
+
+static void free_quote_buf(void *buf)
+{
+	size_t len = PAGE_ALIGN(GET_QUOTE_BUF_SIZE);
+	unsigned int count = len >> PAGE_SHIFT;
+
+	if (set_memory_encrypted((unsigned long)buf, count)) {
+		pr_err("Failed to restore encryption mask for Quote buffer, leak it\n");
+		return;
+	}
+
+	free_pages_exact(buf, len);
+}
+
+static void *alloc_quote_buf(void)
+{
+	size_t len = PAGE_ALIGN(GET_QUOTE_BUF_SIZE);
+	unsigned int count = len >> PAGE_SHIFT;
+	void *addr;
+
+	addr = alloc_pages_exact(len, GFP_KERNEL | __GFP_ZERO);
+	if (!addr)
+		return NULL;
+
+	if (set_memory_decrypted((unsigned long)addr, count))
+		return NULL;
+
+	return addr;
+}
+
+/*
+ * wait_for_quote_completion() - Wait for Quote request completion
+ * @quote_buf: Address of Quote buffer.
+ * @timeout: Timeout in seconds to wait for the Quote generation.
+ *
+ * As per TDX GHCI v1.0 specification, sec titled "TDG.VP.VMCALL<GetQuote>",
+ * the status field in the Quote buffer will be set to GET_QUOTE_IN_FLIGHT
+ * while VMM processes the GetQuote request, and will change it to success
+ * or error code after processing is complete. So wait till the status
+ * changes from GET_QUOTE_IN_FLIGHT or the request being timed out.
+ */
+static int wait_for_quote_completion(struct tdx_quote_buf *quote_buf, u32 timeout)
+{
+	int i = 0;
+
+	/*
+	 * Quote requests usually take a few seconds to complete, so waking up
+	 * once per second to recheck the status is fine for this use case.
+	 */
+	while (quote_buf->status == GET_QUOTE_IN_FLIGHT && i++ < timeout) {
+		if (msleep_interruptible(MSEC_PER_SEC))
+			return -EINTR;
+	}
+
+	return (i == timeout) ? -ETIMEDOUT : 0;
+}
+
+static int tdx_report_new_locked(struct tsm_report *report, void *data)
+{
+	u8 *buf;
+	struct tdx_quote_buf *quote_buf = quote_data;
+	struct tsm_report_desc *desc = &report->desc;
+	u32 out_len;
+	int ret;
+	u64 err;
+
+	/*
+	 * If the previous request is timedout or interrupted, and the
+	 * Quote buf status is still in GET_QUOTE_IN_FLIGHT (owned by
+	 * VMM), don't permit any new request.
+	 */
+	if (quote_buf->status == GET_QUOTE_IN_FLIGHT)
+		return -EBUSY;
+
+	if (desc->inblob_len != TDX_REPORTDATA_LEN)
+		return -EINVAL;
+
+	memset(quote_data, 0, GET_QUOTE_BUF_SIZE);
+
+	/* Update Quote buffer header */
+	quote_buf->version = GET_QUOTE_CMD_VER;
+	quote_buf->in_len = TDX_REPORT_LEN;
+
+	ret = tdx_do_report(KERNEL_SOCKPTR(desc->inblob),
+			    KERNEL_SOCKPTR(quote_buf->data));
+	if (ret)
+		return ret;
+
+	err = tdx_hcall_get_quote(quote_data, GET_QUOTE_BUF_SIZE);
+	if (err) {
+		pr_err("GetQuote hypercall failed, status:%llx\n", err);
+		return -EIO;
+	}
+
+	ret = wait_for_quote_completion(quote_buf, getquote_timeout);
+	if (ret) {
+		pr_err("GetQuote request timedout\n");
+		return ret;
+	}
+
+	if (quote_buf->status != GET_QUOTE_SUCCESS) {
+		pr_debug("GetQuote request failed, status:%llx\n", quote_buf->status);
+		return -EIO;
+	}
+
+	out_len = READ_ONCE(quote_buf->out_len);
+
+	if (out_len > TDX_QUOTE_MAX_LEN)
+		return -EFBIG;
+
+	buf = kvmemdup(quote_buf->data, out_len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	report->outblob = buf;
+	report->outblob_len = out_len;
+
+	/*
+	 * TODO: parse the PEM-formatted cert chain out of the quote buffer when
+	 * provided
+	 */
+
+	return ret;
+}
+
+static int tdx_report_new(struct tsm_report *report, void *data)
+{
+	scoped_cond_guard(mutex_intr, return -EINTR, &quote_lock)
+		return tdx_report_new_locked(report, data);
+}
+
+static bool tdx_report_attr_visible(int n)
+{
+	switch (n) {
+	case TSM_REPORT_GENERATION:
+	case TSM_REPORT_PROVIDER:
+		return true;
+	}
+
+	return false;
+}
+
+static bool tdx_report_bin_attr_visible(int n)
+{
+	switch (n) {
+	case TSM_REPORT_INBLOB:
+	case TSM_REPORT_OUTBLOB:
+		return true;
+	}
+
+	return false;
+}
+
+static long tdx_guest_ioctl(struct file *file, unsigned int cmd,
+			    unsigned long arg)
+{
+	switch (cmd) {
+	case TDX_CMD_GET_REPORT0:
+		return tdx_get_report0((struct tdx_report_req __user *)arg);
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct file_operations tdx_guest_fops = {
+	.owner = THIS_MODULE,
+	.unlocked_ioctl = tdx_guest_ioctl,
+};
+
+static const struct attribute_group *tdx_attr_groups[] = {
+	NULL, /* measurements */
+	NULL
+};
+
+static struct miscdevice tdx_misc_dev = {
+	.name = KBUILD_MODNAME,
+	.minor = MISC_DYNAMIC_MINOR,
+	.fops = &tdx_guest_fops,
+	.groups = tdx_attr_groups,
+};
+
+static const struct x86_cpu_id tdx_guest_ids[] = {
+	X86_MATCH_FEATURE(X86_FEATURE_TDX_GUEST, NULL),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, tdx_guest_ids);
+
+static const struct tsm_report_ops tdx_tsm_ops = {
+	.name = KBUILD_MODNAME,
+	.report_new = tdx_report_new,
+	.report_attr_visible = tdx_report_attr_visible,
+	.report_bin_attr_visible = tdx_report_bin_attr_visible,
+};
+
+static int __init tdx_guest_init(void)
+{
+	int ret;
+
+	if (!x86_match_cpu(tdx_guest_ids))
+		return -ENODEV;
+
+	tdx_attr_groups[0] = tdx_mr_init();
+	if (IS_ERR(tdx_attr_groups[0]))
+		return PTR_ERR(tdx_attr_groups[0]);
+
+	ret = misc_register(&tdx_misc_dev);
+	if (ret)
+		goto deinit_mr;
+
+	quote_data = alloc_quote_buf();
+	if (!quote_data) {
+		pr_err("Failed to allocate Quote buffer\n");
+		ret = -ENOMEM;
+		goto free_misc;
+	}
+
+	ret = tsm_report_register(&tdx_tsm_ops, NULL);
+	if (ret)
+		goto free_quote;
+
+	return 0;
+
+free_quote:
+	free_quote_buf(quote_data);
+free_misc:
+	misc_deregister(&tdx_misc_dev);
+deinit_mr:
+	tdx_mr_deinit(tdx_attr_groups[0]);
+
+	return ret;
+}
+module_init(tdx_guest_init);
+
+static void __exit tdx_guest_exit(void)
+{
+	tsm_report_unregister(&tdx_tsm_ops);
+	free_quote_buf(quote_data);
+	misc_deregister(&tdx_misc_dev);
+	tdx_mr_deinit(tdx_attr_groups[0]);
+}
+module_exit(tdx_guest_exit);
+
+MODULE_AUTHOR("Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>");
+MODULE_DESCRIPTION("TDX Guest Driver");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/virt/coco/tdx-host/Kconfig

@@ -0,0 +1,6 @@
+config TDX_HOST_SERVICES
+	tristate
+	depends on INTEL_TDX_HOST
+	select FW_LOADER
+	select FW_UPLOAD
+	default m

linux-7.2.3/drivers/virt/coco/tdx-host/Makefile

@@ -0,0 +1 @@
+obj-$(CONFIG_TDX_HOST_SERVICES) += tdx-host.o

linux-7.2.3/drivers/virt/coco/tdx-host/tdx-host.c

@@ -0,0 +1,238 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * TDX host user interface driver
+ *
+ * Copyright (C) 2025 Intel Corporation
+ */
+
+#include <linux/device/faux.h>
+#include <linux/firmware.h>
+#include <linux/module.h>
+#include <linux/sysfs.h>
+
+#include <asm/cpu_device_id.h>
+#include <asm/seamldr.h>
+#include <asm/tdx.h>
+
+static const struct x86_cpu_id tdx_host_ids[] = {
+	X86_MATCH_FEATURE(X86_FEATURE_TDX_HOST_PLATFORM, NULL),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, tdx_host_ids);
+
+static ssize_t version_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	const struct tdx_sys_info *tdx_sysinfo = tdx_get_sysinfo();
+	const struct tdx_sys_info_version *ver;
+	int ret;
+
+	if (!tdx_sysinfo)
+		return -ENXIO;
+
+	/*
+	 * The version number can change during an update.
+	 * Lock out updates while printing the version.
+	 */
+	seamldr_lock_module_update();
+
+	ver = &tdx_sysinfo->version;
+	ret = sysfs_emit(buf, TDX_VERSION_FMT "\n", ver->major_version,
+						    ver->minor_version,
+						    ver->update_version);
+	seamldr_unlock_module_update();
+
+	return ret;
+}
+static DEVICE_ATTR_RO(version);
+
+static struct attribute *tdx_host_attrs[] = {
+	&dev_attr_version.attr,
+	NULL,
+};
+
+static const struct attribute_group tdx_host_group = {
+	.attrs = tdx_host_attrs,
+};
+
+static ssize_t seamldr_version_show(struct device *dev, struct device_attribute *attr,
+				    char *buf)
+{
+	struct seamldr_info info;
+	int ret;
+
+	ret = seamldr_get_info(&info);
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, TDX_VERSION_FMT "\n", info.major_version,
+						     info.minor_version,
+						     info.update_version);
+}
+
+static ssize_t num_remaining_updates_show(struct device *dev,
+					  struct device_attribute *attr,
+					  char *buf)
+{
+	struct seamldr_info info;
+	int ret;
+
+	ret = seamldr_get_info(&info);
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%u\n", info.num_remaining_updates);
+}
+
+/*
+ * These attributes are intended for managing TDX module updates. Reading
+ * them issues a slow, serialized P-SEAMLDR query, so keep them admin-only.
+ */
+static DEVICE_ATTR_ADMIN_RO(seamldr_version);
+static DEVICE_ATTR_ADMIN_RO(num_remaining_updates);
+
+static struct attribute *seamldr_attrs[] = {
+	&dev_attr_seamldr_version.attr,
+	&dev_attr_num_remaining_updates.attr,
+	NULL,
+};
+
+static bool supports_runtime_update(void)
+{
+	const struct tdx_sys_info *sysinfo = tdx_get_sysinfo();
+
+	if (!sysinfo)
+		return false;
+
+	if (!tdx_supports_runtime_update(sysinfo))
+		return false;
+
+	/*
+	 * This bug makes P-SEAMLDR calls clobber the current VMCS
+	 * which breaks KVM. Avoid P-SEAMLDR calls by hiding all
+	 * attributes if the CPU has this bug.
+	 */
+	if (boot_cpu_has_bug(X86_BUG_SEAMRET_INVD_VMCS))
+		return false;
+
+	return true;
+}
+
+static umode_t seamldr_group_visible(struct kobject *kobj, struct attribute *attr, int idx)
+{
+	if (!supports_runtime_update())
+		return 0;
+
+	return attr->mode;
+}
+
+static const struct attribute_group seamldr_group = {
+	.attrs = seamldr_attrs,
+	.is_visible = seamldr_group_visible,
+};
+
+static const struct attribute_group *tdx_host_groups[] = {
+	&tdx_host_group,
+	&seamldr_group,
+	NULL,
+};
+
+static enum fw_upload_err tdx_fw_prepare(struct fw_upload *fwl,
+					 const u8 *data, u32 data_len)
+{
+	return FW_UPLOAD_ERR_NONE;
+}
+
+static enum fw_upload_err tdx_fw_write(struct fw_upload *fwl, const u8 *data,
+				       u32 offset, u32 data_len, u32 *written)
+{
+	int ret;
+
+	ret = seamldr_install_module(data, data_len);
+	switch (ret) {
+	case 0:
+		*written = data_len;
+		return FW_UPLOAD_ERR_NONE;
+	default:
+		return FW_UPLOAD_ERR_FW_INVALID;
+	}
+}
+
+static enum fw_upload_err tdx_fw_poll_complete(struct fw_upload *fwl)
+{
+	/*
+	 * The upload completed during tdx_fw_write().
+	 * Never poll for completion.
+	 */
+	return FW_UPLOAD_ERR_NONE;
+}
+
+static void tdx_fw_cancel(struct fw_upload *fwl)
+{
+	/*
+	 * TDX module updates are not cancellable.
+	 * Provide a no-op callback to satisfy fw_upload_ops.
+	 */
+}
+
+static const struct fw_upload_ops tdx_fw_ops = {
+	.prepare	= tdx_fw_prepare,
+	.write		= tdx_fw_write,
+	.poll_complete	= tdx_fw_poll_complete,
+	.cancel		= tdx_fw_cancel,
+};
+
+static void seamldr_deinit(void *tdx_fwl)
+{
+	firmware_upload_unregister(tdx_fwl);
+}
+
+static int seamldr_init(struct device *dev)
+{
+	struct fw_upload *tdx_fwl;
+
+	if (!supports_runtime_update())
+		return 0;
+
+	tdx_fwl = firmware_upload_register(THIS_MODULE, dev, "tdx_module",
+					   &tdx_fw_ops, NULL);
+	if (IS_ERR(tdx_fwl))
+		return PTR_ERR(tdx_fwl);
+
+	return devm_add_action_or_reset(dev, seamldr_deinit, tdx_fwl);
+}
+
+static int tdx_host_probe(struct faux_device *fdev)
+{
+	return seamldr_init(&fdev->dev);
+}
+
+static const struct faux_device_ops tdx_host_ops = {
+	.probe		= tdx_host_probe,
+};
+
+static struct faux_device *fdev;
+
+static int __init tdx_host_init(void)
+{
+	if (!x86_match_cpu(tdx_host_ids) || !tdx_get_sysinfo())
+		return -ENODEV;
+
+	fdev = faux_device_create_with_groups(KBUILD_MODNAME, NULL,
+					      &tdx_host_ops,
+					      tdx_host_groups);
+	if (!fdev)
+		return -ENODEV;
+
+	return 0;
+}
+module_init(tdx_host_init);
+
+static void __exit tdx_host_exit(void)
+{
+	faux_device_destroy(fdev);
+}
+module_exit(tdx_host_exit);
+
+MODULE_DESCRIPTION("TDX Host Services");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/virt/coco/tsm-core.c

@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright(c) 2024-2025 Intel Corporation. All rights reserved. */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/tsm.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/cleanup.h>
+#include <linux/pci-tsm.h>
+
+static void tsm_release(struct device *);
+static const struct class tsm_class = {
+	.name		= "tsm",
+	.dev_release	= tsm_release
+};
+static DEFINE_IDA(tsm_ida);
+
+static int match_id(struct device *dev, const void *data)
+{
+	struct tsm_dev *tsm_dev = container_of(dev, struct tsm_dev, dev);
+	int id = *(const int *)data;
+
+	return tsm_dev->id == id;
+}
+
+struct tsm_dev *find_tsm_dev(int id)
+{
+	struct device *dev = class_find_device(&tsm_class, NULL, &id, match_id);
+
+	if (!dev)
+		return NULL;
+	return container_of(dev, struct tsm_dev, dev);
+}
+
+static struct tsm_dev *alloc_tsm_dev(struct device *parent)
+{
+	struct device *dev;
+	int id;
+
+	struct tsm_dev *tsm_dev __free(kfree) =
+		kzalloc_obj(*tsm_dev);
+	if (!tsm_dev)
+		return ERR_PTR(-ENOMEM);
+
+	id = ida_alloc(&tsm_ida, GFP_KERNEL);
+	if (id < 0)
+		return ERR_PTR(id);
+
+	tsm_dev->id = id;
+	dev = &tsm_dev->dev;
+	dev->parent = parent;
+	dev->class = &tsm_class;
+	device_initialize(dev);
+
+	return no_free_ptr(tsm_dev);
+}
+
+static struct tsm_dev *tsm_register_pci_or_reset(struct tsm_dev *tsm_dev,
+						 struct pci_tsm_ops *pci_ops)
+{
+	int rc;
+
+	if (!pci_ops)
+		return tsm_dev;
+
+	tsm_dev->pci_ops = pci_ops;
+	rc = pci_tsm_register(tsm_dev);
+	if (rc) {
+		dev_err(tsm_dev->dev.parent,
+			"PCI/TSM registration failure: %d\n", rc);
+		device_unregister(&tsm_dev->dev);
+		return ERR_PTR(rc);
+	}
+
+	/* Notify TSM userspace that PCI/TSM operations are now possible */
+	kobject_uevent(&tsm_dev->dev.kobj, KOBJ_CHANGE);
+	return tsm_dev;
+}
+
+struct tsm_dev *tsm_register(struct device *parent, struct pci_tsm_ops *pci_ops)
+{
+	struct tsm_dev *tsm_dev __free(put_tsm_dev) = alloc_tsm_dev(parent);
+	struct device *dev;
+	int rc;
+
+	if (IS_ERR(tsm_dev))
+		return tsm_dev;
+
+	dev = &tsm_dev->dev;
+	rc = dev_set_name(dev, "tsm%d", tsm_dev->id);
+	if (rc)
+		return ERR_PTR(rc);
+
+	rc = device_add(dev);
+	if (rc)
+		return ERR_PTR(rc);
+
+	return tsm_register_pci_or_reset(no_free_ptr(tsm_dev), pci_ops);
+}
+EXPORT_SYMBOL_GPL(tsm_register);
+
+void tsm_unregister(struct tsm_dev *tsm_dev)
+{
+	if (tsm_dev->pci_ops)
+		pci_tsm_unregister(tsm_dev);
+	device_unregister(&tsm_dev->dev);
+}
+EXPORT_SYMBOL_GPL(tsm_unregister);
+
+static void tsm_release(struct device *dev)
+{
+	struct tsm_dev *tsm_dev = container_of(dev, typeof(*tsm_dev), dev);
+
+	ida_free(&tsm_ida, tsm_dev->id);
+	kfree(tsm_dev);
+}
+
+static int __init tsm_init(void)
+{
+	return class_register(&tsm_class);
+}
+module_init(tsm_init)
+
+static void __exit tsm_exit(void)
+{
+	class_unregister(&tsm_class);
+}
+module_exit(tsm_exit)
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("TEE Security Manager Class Device");

linux-7.2.3/drivers/virt/fsl_hypervisor.c

@@ -0,0 +1,932 @@
+/*
+ * Freescale Hypervisor Management Driver
+
+ * Copyright (C) 2008-2011 Freescale Semiconductor, Inc.
+ * Author: Timur Tabi <timur@freescale.com>
+ *
+ * This file is licensed under the terms of the GNU General Public License
+ * version 2.  This program is licensed "as is" without any warranty of any
+ * kind, whether express or implied.
+ *
+ * The Freescale hypervisor management driver provides several services to
+ * drivers and applications related to the Freescale hypervisor:
+ *
+ * 1. An ioctl interface for querying and managing partitions.
+ *
+ * 2. A file interface to reading incoming doorbells.
+ *
+ * 3. An interrupt handler for shutting down the partition upon receiving the
+ *    shutdown doorbell from a manager partition.
+ *
+ * 4. A kernel interface for receiving callbacks when a managed partition
+ *    shuts down.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/err.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/pagemap.h>
+#include <linux/slab.h>
+#include <linux/poll.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/reboot.h>
+#include <linux/uaccess.h>
+#include <linux/notifier.h>
+#include <linux/interrupt.h>
+
+#include <linux/io.h>
+#include <asm/fsl_hcalls.h>
+
+#include <linux/fsl_hypervisor.h>
+
+static BLOCKING_NOTIFIER_HEAD(failover_subscribers);
+
+/*
+ * Ioctl interface for FSL_HV_IOCTL_PARTITION_RESTART
+ *
+ * Restart a running partition
+ */
+static long ioctl_restart(struct fsl_hv_ioctl_restart __user *p)
+{
+	struct fsl_hv_ioctl_restart param;
+
+	/* Get the parameters from the user */
+	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_restart)))
+		return -EFAULT;
+
+	param.ret = fh_partition_restart(param.partition);
+
+	if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
+		return -EFAULT;
+
+	return 0;
+}
+
+/*
+ * Ioctl interface for FSL_HV_IOCTL_PARTITION_STATUS
+ *
+ * Query the status of a partition
+ */
+static long ioctl_status(struct fsl_hv_ioctl_status __user *p)
+{
+	struct fsl_hv_ioctl_status param;
+	u32 status;
+
+	/* Get the parameters from the user */
+	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_status)))
+		return -EFAULT;
+
+	param.ret = fh_partition_get_status(param.partition, &status);
+	if (!param.ret)
+		param.status = status;
+
+	if (copy_to_user(p, &param, sizeof(struct fsl_hv_ioctl_status)))
+		return -EFAULT;
+
+	return 0;
+}
+
+/*
+ * Ioctl interface for FSL_HV_IOCTL_PARTITION_START
+ *
+ * Start a stopped partition.
+ */
+static long ioctl_start(struct fsl_hv_ioctl_start __user *p)
+{
+	struct fsl_hv_ioctl_start param;
+
+	/* Get the parameters from the user */
+	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_start)))
+		return -EFAULT;
+
+	param.ret = fh_partition_start(param.partition, param.entry_point,
+				       param.load);
+
+	if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
+		return -EFAULT;
+
+	return 0;
+}
+
+/*
+ * Ioctl interface for FSL_HV_IOCTL_PARTITION_STOP
+ *
+ * Stop a running partition
+ */
+static long ioctl_stop(struct fsl_hv_ioctl_stop __user *p)
+{
+	struct fsl_hv_ioctl_stop param;
+
+	/* Get the parameters from the user */
+	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_stop)))
+		return -EFAULT;
+
+	param.ret = fh_partition_stop(param.partition);
+
+	if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
+		return -EFAULT;
+
+	return 0;
+}
+
+/*
+ * Ioctl interface for FSL_HV_IOCTL_MEMCPY
+ *
+ * The FH_MEMCPY hypercall takes an array of address/address/size structures
+ * to represent the data being copied.  As a convenience to the user, this
+ * ioctl takes a user-create buffer and a pointer to a guest physically
+ * contiguous buffer in the remote partition, and creates the
+ * address/address/size array for the hypercall.
+ */
+static long ioctl_memcpy(struct fsl_hv_ioctl_memcpy __user *p)
+{
+	struct fsl_hv_ioctl_memcpy param;
+
+	struct page **pages = NULL;
+	void *sg_list_unaligned = NULL;
+	struct fh_sg_list *sg_list = NULL;
+
+	unsigned int num_pages;
+	unsigned long lb_offset; /* Offset within a page of the local buffer */
+
+	unsigned int i;
+	long ret = 0;
+	int num_pinned = 0; /* return value from get_user_pages_fast() */
+	phys_addr_t remote_paddr; /* The next address in the remote buffer */
+	uint32_t count; /* The number of bytes left to copy */
+
+	/* Get the parameters from the user */
+	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_memcpy)))
+		return -EFAULT;
+
+	/*
+	 * One partition must be local, the other must be remote.  In other
+	 * words, if source and target are both -1, or are both not -1, then
+	 * return an error.
+	 */
+	if ((param.source == -1) == (param.target == -1))
+		return -EINVAL;
+
+	/*
+	 * The array of pages returned by get_user_pages_fast() covers only
+	 * page-aligned memory.  Since the user buffer is probably not
+	 * page-aligned, we need to handle the discrepancy.
+	 *
+	 * We calculate the offset within a page of the S/G list, and make
+	 * adjustments accordingly.  This will result in a page list that looks
+	 * like this:
+	 *
+	 *      ----    <-- first page starts before the buffer
+	 *     |    |
+	 *     |////|-> ----
+	 *     |////|  |    |
+	 *      ----   |    |
+	 *             |    |
+	 *      ----   |    |
+	 *     |////|  |    |
+	 *     |////|  |    |
+	 *     |////|  |    |
+	 *      ----   |    |
+	 *             |    |
+	 *      ----   |    |
+	 *     |////|  |    |
+	 *     |////|  |    |
+	 *     |////|  |    |
+	 *      ----   |    |
+	 *             |    |
+	 *      ----   |    |
+	 *     |////|  |    |
+	 *     |////|-> ----
+	 *     |    |   <-- last page ends after the buffer
+	 *      ----
+	 *
+	 * The distance between the start of the first page and the start of the
+	 * buffer is lb_offset.  The hashed (///) areas are the parts of the
+	 * page list that contain the actual buffer.
+	 *
+	 * The advantage of this approach is that the number of pages is
+	 * equal to the number of entries in the S/G list that we give to the
+	 * hypervisor.
+	 */
+	lb_offset = param.local_vaddr & (PAGE_SIZE - 1);
+	if (param.count == 0 ||
+	    param.count > U64_MAX - lb_offset - PAGE_SIZE + 1)
+		return -EINVAL;
+	num_pages = (param.count + lb_offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+	/* Allocate the buffers we need */
+
+	/*
+	 * 'pages' is an array of struct page pointers that's initialized by
+	 * get_user_pages_fast().
+	 */
+	pages = kzalloc_objs(struct page *, num_pages);
+	if (!pages) {
+		pr_debug("fsl-hv: could not allocate page list\n");
+		return -ENOMEM;
+	}
+
+	/*
+	 * sg_list is the list of fh_sg_list objects that we pass to the
+	 * hypervisor.
+	 */
+	sg_list_unaligned = kmalloc(num_pages * sizeof(struct fh_sg_list) +
+		sizeof(struct fh_sg_list) - 1, GFP_KERNEL);
+	if (!sg_list_unaligned) {
+		pr_debug("fsl-hv: could not allocate S/G list\n");
+		ret = -ENOMEM;
+		goto free_pages;
+	}
+	sg_list = PTR_ALIGN(sg_list_unaligned, sizeof(struct fh_sg_list));
+
+	/* Get the physical addresses of the source buffer */
+	num_pinned = get_user_pages_fast(param.local_vaddr - lb_offset,
+		num_pages, param.source != -1 ? FOLL_WRITE : 0, pages);
+
+	if (num_pinned != num_pages) {
+		pr_debug("fsl-hv: could not lock source buffer\n");
+		ret = (num_pinned < 0) ? num_pinned : -EFAULT;
+		goto exit;
+	}
+
+	/*
+	 * Build the fh_sg_list[] array.  The first page is special
+	 * because it's misaligned.
+	 */
+	if (param.source == -1) {
+		sg_list[0].source = page_to_phys(pages[0]) + lb_offset;
+		sg_list[0].target = param.remote_paddr;
+	} else {
+		sg_list[0].source = param.remote_paddr;
+		sg_list[0].target = page_to_phys(pages[0]) + lb_offset;
+	}
+	sg_list[0].size = min_t(uint64_t, param.count, PAGE_SIZE - lb_offset);
+
+	remote_paddr = param.remote_paddr + sg_list[0].size;
+	count = param.count - sg_list[0].size;
+
+	for (i = 1; i < num_pages; i++) {
+		if (param.source == -1) {
+			/* local to remote */
+			sg_list[i].source = page_to_phys(pages[i]);
+			sg_list[i].target = remote_paddr;
+		} else {
+			/* remote to local */
+			sg_list[i].source = remote_paddr;
+			sg_list[i].target = page_to_phys(pages[i]);
+		}
+		sg_list[i].size = min_t(uint64_t, count, PAGE_SIZE);
+
+		remote_paddr += sg_list[i].size;
+		count -= sg_list[i].size;
+	}
+
+	param.ret = fh_partition_memcpy(param.source, param.target,
+		virt_to_phys(sg_list), num_pages);
+
+exit:
+	if (pages && (num_pinned > 0)) {
+		for (i = 0; i < num_pinned; i++)
+			put_page(pages[i]);
+	}
+
+	kfree(sg_list_unaligned);
+free_pages:
+	kfree(pages);
+
+	if (!ret)
+		if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
+			return -EFAULT;
+
+	return ret;
+}
+
+/*
+ * Ioctl interface for FSL_HV_IOCTL_DOORBELL
+ *
+ * Ring a doorbell
+ */
+static long ioctl_doorbell(struct fsl_hv_ioctl_doorbell __user *p)
+{
+	struct fsl_hv_ioctl_doorbell param;
+
+	/* Get the parameters from the user. */
+	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_doorbell)))
+		return -EFAULT;
+
+	param.ret = ev_doorbell_send(param.doorbell);
+
+	if (copy_to_user(&p->ret, &param.ret, sizeof(__u32)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long ioctl_dtprop(struct fsl_hv_ioctl_prop __user *p, int set)
+{
+	struct fsl_hv_ioctl_prop param;
+	char __user *upath, *upropname;
+	void __user *upropval;
+	char *path, *propname;
+	void *propval;
+	int ret = 0;
+
+	/* Get the parameters from the user. */
+	if (copy_from_user(&param, p, sizeof(struct fsl_hv_ioctl_prop)))
+		return -EFAULT;
+
+	upath = (char __user *)(uintptr_t)param.path;
+	upropname = (char __user *)(uintptr_t)param.propname;
+	upropval = (void __user *)(uintptr_t)param.propval;
+
+	path = strndup_user(upath, FH_DTPROP_MAX_PATHLEN);
+	if (IS_ERR(path))
+		return PTR_ERR(path);
+
+	propname = strndup_user(upropname, FH_DTPROP_MAX_PATHLEN);
+	if (IS_ERR(propname)) {
+		ret = PTR_ERR(propname);
+		goto err_free_path;
+	}
+
+	if (param.proplen > FH_DTPROP_MAX_PROPLEN) {
+		ret = -EINVAL;
+		goto err_free_propname;
+	}
+
+	propval = kmalloc(param.proplen, GFP_KERNEL);
+	if (!propval) {
+		ret = -ENOMEM;
+		goto err_free_propname;
+	}
+
+	if (set) {
+		if (copy_from_user(propval, upropval, param.proplen)) {
+			ret = -EFAULT;
+			goto err_free_propval;
+		}
+
+		param.ret = fh_partition_set_dtprop(param.handle,
+						    virt_to_phys(path),
+						    virt_to_phys(propname),
+						    virt_to_phys(propval),
+						    param.proplen);
+	} else {
+		param.ret = fh_partition_get_dtprop(param.handle,
+						    virt_to_phys(path),
+						    virt_to_phys(propname),
+						    virt_to_phys(propval),
+						    &param.proplen);
+
+		if (param.ret == 0) {
+			if (copy_to_user(upropval, propval, param.proplen) ||
+			    put_user(param.proplen, &p->proplen)) {
+				ret = -EFAULT;
+				goto err_free_propval;
+			}
+		}
+	}
+
+	if (put_user(param.ret, &p->ret))
+		ret = -EFAULT;
+
+err_free_propval:
+	kfree(propval);
+err_free_propname:
+	kfree(propname);
+err_free_path:
+	kfree(path);
+
+	return ret;
+}
+
+/*
+ * Ioctl main entry point
+ */
+static long fsl_hv_ioctl(struct file *file, unsigned int cmd,
+			 unsigned long argaddr)
+{
+	void __user *arg = (void __user *)argaddr;
+	long ret;
+
+	switch (cmd) {
+	case FSL_HV_IOCTL_PARTITION_RESTART:
+		ret = ioctl_restart(arg);
+		break;
+	case FSL_HV_IOCTL_PARTITION_GET_STATUS:
+		ret = ioctl_status(arg);
+		break;
+	case FSL_HV_IOCTL_PARTITION_START:
+		ret = ioctl_start(arg);
+		break;
+	case FSL_HV_IOCTL_PARTITION_STOP:
+		ret = ioctl_stop(arg);
+		break;
+	case FSL_HV_IOCTL_MEMCPY:
+		ret = ioctl_memcpy(arg);
+		break;
+	case FSL_HV_IOCTL_DOORBELL:
+		ret = ioctl_doorbell(arg);
+		break;
+	case FSL_HV_IOCTL_GETPROP:
+		ret = ioctl_dtprop(arg, 0);
+		break;
+	case FSL_HV_IOCTL_SETPROP:
+		ret = ioctl_dtprop(arg, 1);
+		break;
+	default:
+		pr_debug("fsl-hv: bad ioctl dir=%u type=%u cmd=%u size=%u\n",
+			 _IOC_DIR(cmd), _IOC_TYPE(cmd), _IOC_NR(cmd),
+			 _IOC_SIZE(cmd));
+		return -ENOTTY;
+	}
+
+	return ret;
+}
+
+/* Linked list of processes that have us open */
+static struct list_head db_list;
+
+/* spinlock for db_list */
+static DEFINE_SPINLOCK(db_list_lock);
+
+/* The size of the doorbell event queue.  This must be a power of two. */
+#define QSIZE	16
+
+/* Returns the next head/tail pointer, wrapping around the queue if necessary */
+#define nextp(x) (((x) + 1) & (QSIZE - 1))
+
+/* Per-open data structure */
+struct doorbell_queue {
+	struct list_head list;
+	spinlock_t lock;
+	wait_queue_head_t wait;
+	unsigned int head;
+	unsigned int tail;
+	uint32_t q[QSIZE];
+};
+
+/* Linked list of ISRs that we registered */
+struct list_head isr_list;
+
+/* Per-ISR data structure */
+struct doorbell_isr {
+	struct list_head list;
+	unsigned int irq;
+	uint32_t doorbell;	/* The doorbell handle */
+	uint32_t partition;	/* The partition handle, if used */
+};
+
+/*
+ * Add a doorbell to all of the doorbell queues
+ */
+static void fsl_hv_queue_doorbell(uint32_t doorbell)
+{
+	struct doorbell_queue *dbq;
+	unsigned long flags;
+
+	/* Prevent another core from modifying db_list */
+	spin_lock_irqsave(&db_list_lock, flags);
+
+	list_for_each_entry(dbq, &db_list, list) {
+		if (dbq->head != nextp(dbq->tail)) {
+			dbq->q[dbq->tail] = doorbell;
+			/*
+			 * This memory barrier eliminates the need to grab
+			 * the spinlock for dbq.
+			 */
+			smp_wmb();
+			dbq->tail = nextp(dbq->tail);
+			wake_up_interruptible(&dbq->wait);
+		}
+	}
+
+	spin_unlock_irqrestore(&db_list_lock, flags);
+}
+
+/*
+ * Interrupt handler for all doorbells
+ *
+ * We use the same interrupt handler for all doorbells.  Whenever a doorbell
+ * is rung, and we receive an interrupt, we just put the handle for that
+ * doorbell (passed to us as *data) into all of the queues.
+ */
+static irqreturn_t fsl_hv_isr(int irq, void *data)
+{
+	fsl_hv_queue_doorbell((uintptr_t) data);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * State change thread function
+ *
+ * The state change notification arrives in an interrupt, but we can't call
+ * blocking_notifier_call_chain() in an interrupt handler.  We could call
+ * atomic_notifier_call_chain(), but that would require the clients' call-back
+ * function to run in interrupt context.  Since we don't want to impose that
+ * restriction on the clients, we use a threaded IRQ to process the
+ * notification in kernel context.
+ */
+static irqreturn_t fsl_hv_state_change_thread(int irq, void *data)
+{
+	struct doorbell_isr *dbisr = data;
+
+	blocking_notifier_call_chain(&failover_subscribers, dbisr->partition,
+				     NULL);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * Interrupt handler for state-change doorbells
+ */
+static irqreturn_t fsl_hv_state_change_isr(int irq, void *data)
+{
+	unsigned int status;
+	struct doorbell_isr *dbisr = data;
+	int ret;
+
+	/* It's still a doorbell, so add it to all the queues. */
+	fsl_hv_queue_doorbell(dbisr->doorbell);
+
+	/* Determine the new state, and if it's stopped, notify the clients. */
+	ret = fh_partition_get_status(dbisr->partition, &status);
+	if (!ret && (status == FH_PARTITION_STOPPED))
+		return IRQ_WAKE_THREAD;
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * Returns a bitmask indicating whether a read will block
+ */
+static __poll_t fsl_hv_poll(struct file *filp, struct poll_table_struct *p)
+{
+	struct doorbell_queue *dbq = filp->private_data;
+	unsigned long flags;
+	__poll_t mask;
+
+	spin_lock_irqsave(&dbq->lock, flags);
+
+	poll_wait(filp, &dbq->wait, p);
+	mask = (dbq->head == dbq->tail) ? 0 : (EPOLLIN | EPOLLRDNORM);
+
+	spin_unlock_irqrestore(&dbq->lock, flags);
+
+	return mask;
+}
+
+/*
+ * Return the handles for any incoming doorbells
+ *
+ * If there are doorbell handles in the queue for this open instance, then
+ * return them to the caller as an array of 32-bit integers.  Otherwise,
+ * block until there is at least one handle to return.
+ */
+static ssize_t fsl_hv_read(struct file *filp, char __user *buf, size_t len,
+			   loff_t *off)
+{
+	struct doorbell_queue *dbq = filp->private_data;
+	uint32_t __user *p = (uint32_t __user *) buf; /* for put_user() */
+	unsigned long flags;
+	ssize_t count = 0;
+
+	/* Make sure we stop when the user buffer is full. */
+	while (len >= sizeof(uint32_t)) {
+		uint32_t dbell;	/* Local copy of doorbell queue data */
+
+		spin_lock_irqsave(&dbq->lock, flags);
+
+		/*
+		 * If the queue is empty, then either we're done or we need
+		 * to block.  If the application specified O_NONBLOCK, then
+		 * we return the appropriate error code.
+		 */
+		if (dbq->head == dbq->tail) {
+			spin_unlock_irqrestore(&dbq->lock, flags);
+			if (count)
+				break;
+			if (filp->f_flags & O_NONBLOCK)
+				return -EAGAIN;
+			if (wait_event_interruptible(dbq->wait,
+						     dbq->head != dbq->tail))
+				return -ERESTARTSYS;
+			continue;
+		}
+
+		/*
+		 * Even though we have an smp_wmb() in the ISR, the core
+		 * might speculatively execute the "dbell = ..." below while
+		 * it's evaluating the if-statement above.  In that case, the
+		 * value put into dbell could be stale if the core accepts the
+		 * speculation. To prevent that, we need a read memory barrier
+		 * here as well.
+		 */
+		smp_rmb();
+
+		/* Copy the data to a temporary local buffer, because
+		 * we can't call copy_to_user() from inside a spinlock
+		 */
+		dbell = dbq->q[dbq->head];
+		dbq->head = nextp(dbq->head);
+
+		spin_unlock_irqrestore(&dbq->lock, flags);
+
+		if (put_user(dbell, p))
+			return -EFAULT;
+		p++;
+		count += sizeof(uint32_t);
+		len -= sizeof(uint32_t);
+	}
+
+	return count;
+}
+
+/*
+ * Open the driver and prepare for reading doorbells.
+ *
+ * Every time an application opens the driver, we create a doorbell queue
+ * for that file handle.  This queue is used for any incoming doorbells.
+ */
+static int fsl_hv_open(struct inode *inode, struct file *filp)
+{
+	struct doorbell_queue *dbq;
+	unsigned long flags;
+
+	dbq = kzalloc_obj(struct doorbell_queue);
+	if (!dbq) {
+		pr_err("fsl-hv: out of memory\n");
+		return -ENOMEM;
+	}
+
+	spin_lock_init(&dbq->lock);
+	init_waitqueue_head(&dbq->wait);
+
+	spin_lock_irqsave(&db_list_lock, flags);
+	list_add(&dbq->list, &db_list);
+	spin_unlock_irqrestore(&db_list_lock, flags);
+
+	filp->private_data = dbq;
+
+	return 0;
+}
+
+/*
+ * Close the driver
+ */
+static int fsl_hv_close(struct inode *inode, struct file *filp)
+{
+	struct doorbell_queue *dbq = filp->private_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&db_list_lock, flags);
+	list_del(&dbq->list);
+	spin_unlock_irqrestore(&db_list_lock, flags);
+
+	kfree(dbq);
+
+	return 0;
+}
+
+static const struct file_operations fsl_hv_fops = {
+	.owner = THIS_MODULE,
+	.open = fsl_hv_open,
+	.release = fsl_hv_close,
+	.poll = fsl_hv_poll,
+	.read = fsl_hv_read,
+	.unlocked_ioctl = fsl_hv_ioctl,
+	.compat_ioctl = compat_ptr_ioctl,
+};
+
+static struct miscdevice fsl_hv_misc_dev = {
+	MISC_DYNAMIC_MINOR,
+	"fsl-hv",
+	&fsl_hv_fops
+};
+
+static irqreturn_t fsl_hv_shutdown_isr(int irq, void *data)
+{
+	orderly_poweroff(false);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * Returns the handle of the parent of the given node
+ *
+ * The handle is the value of the 'hv-handle' property
+ */
+static int get_parent_handle(struct device_node *np)
+{
+	struct device_node *parent;
+	const uint32_t *prop;
+	uint32_t handle;
+	int len;
+
+	parent = of_get_parent(np);
+	if (!parent)
+		/* It's not really possible for this to fail */
+		return -ENODEV;
+
+	/*
+	 * The proper name for the handle property is "hv-handle", but some
+	 * older versions of the hypervisor used "reg".
+	 */
+	prop = of_get_property(parent, "hv-handle", &len);
+	if (!prop)
+		prop = of_get_property(parent, "reg", &len);
+
+	if (!prop || (len != sizeof(uint32_t))) {
+		/* This can happen only if the node is malformed */
+		of_node_put(parent);
+		return -ENODEV;
+	}
+
+	handle = be32_to_cpup(prop);
+	of_node_put(parent);
+
+	return handle;
+}
+
+/*
+ * Register a callback for failover events
+ *
+ * This function is called by device drivers to register their callback
+ * functions for fail-over events.
+ */
+int fsl_hv_failover_register(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&failover_subscribers, nb);
+}
+EXPORT_SYMBOL(fsl_hv_failover_register);
+
+/*
+ * Unregister a callback for failover events
+ */
+int fsl_hv_failover_unregister(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_unregister(&failover_subscribers, nb);
+}
+EXPORT_SYMBOL(fsl_hv_failover_unregister);
+
+/*
+ * Return TRUE if we're running under FSL hypervisor
+ *
+ * This function checks to see if we're running under the Freescale
+ * hypervisor, and returns zero if we're not, or non-zero if we are.
+ *
+ * First, it checks if MSR[GS]==1, which means we're running under some
+ * hypervisor.  Then it checks if there is a hypervisor node in the device
+ * tree.  Currently, that means there needs to be a node in the root called
+ * "hypervisor" and which has a property named "fsl,hv-version".
+ */
+static int has_fsl_hypervisor(void)
+{
+	struct device_node *node;
+	int ret;
+
+	node = of_find_node_by_path("/hypervisor");
+	if (!node)
+		return 0;
+
+	ret = of_property_present(node, "fsl,hv-version");
+
+	of_node_put(node);
+
+	return ret;
+}
+
+/*
+ * Freescale hypervisor management driver init
+ *
+ * This function is called when this module is loaded.
+ *
+ * Register ourselves as a miscellaneous driver.  This will register the
+ * fops structure and create the right sysfs entries for udev.
+ */
+static int __init fsl_hypervisor_init(void)
+{
+	struct device_node *np;
+	struct doorbell_isr *dbisr, *n;
+	int ret;
+
+	pr_info("Freescale hypervisor management driver\n");
+
+	if (!has_fsl_hypervisor()) {
+		pr_info("fsl-hv: no hypervisor found\n");
+		return -ENODEV;
+	}
+
+	ret = misc_register(&fsl_hv_misc_dev);
+	if (ret) {
+		pr_err("fsl-hv: cannot register device\n");
+		return ret;
+	}
+
+	INIT_LIST_HEAD(&db_list);
+	INIT_LIST_HEAD(&isr_list);
+
+	for_each_compatible_node(np, NULL, "epapr,hv-receive-doorbell") {
+		unsigned int irq;
+		const uint32_t *handle;
+
+		handle = of_get_property(np, "interrupts", NULL);
+		irq = irq_of_parse_and_map(np, 0);
+		if (!handle || !irq) {
+			pr_err("fsl-hv: no 'interrupts' property in %pOF node\n",
+				np);
+			continue;
+		}
+
+		dbisr = kzalloc_obj(*dbisr);
+		if (!dbisr)
+			goto out_of_memory;
+
+		dbisr->irq = irq;
+		dbisr->doorbell = be32_to_cpup(handle);
+
+		if (of_device_is_compatible(np, "fsl,hv-shutdown-doorbell")) {
+			/* The shutdown doorbell gets its own ISR */
+			ret = request_irq(irq, fsl_hv_shutdown_isr, 0,
+					  np->name, NULL);
+		} else if (of_device_is_compatible(np,
+			"fsl,hv-state-change-doorbell")) {
+			/*
+			 * The state change doorbell triggers a notification if
+			 * the state of the managed partition changes to
+			 * "stopped". We need a separate interrupt handler for
+			 * that, and we also need to know the handle of the
+			 * target partition, not just the handle of the
+			 * doorbell.
+			 */
+			dbisr->partition = ret = get_parent_handle(np);
+			if (ret < 0) {
+				pr_err("fsl-hv: node %pOF has missing or "
+				       "malformed parent\n", np);
+				kfree(dbisr);
+				continue;
+			}
+			ret = request_threaded_irq(irq, fsl_hv_state_change_isr,
+						   fsl_hv_state_change_thread,
+						   0, np->name, dbisr);
+		} else
+			ret = request_irq(irq, fsl_hv_isr, 0, np->name, dbisr);
+
+		if (ret < 0) {
+			pr_err("fsl-hv: could not request irq %u for node %pOF\n",
+			       irq, np);
+			kfree(dbisr);
+			continue;
+		}
+
+		list_add(&dbisr->list, &isr_list);
+
+		pr_info("fsl-hv: registered handler for doorbell %u\n",
+			dbisr->doorbell);
+	}
+
+	return 0;
+
+out_of_memory:
+	list_for_each_entry_safe(dbisr, n, &isr_list, list) {
+		free_irq(dbisr->irq, dbisr);
+		list_del(&dbisr->list);
+		kfree(dbisr);
+	}
+
+	misc_deregister(&fsl_hv_misc_dev);
+
+	return -ENOMEM;
+}
+
+/*
+ * Freescale hypervisor management driver termination
+ *
+ * This function is called when this driver is unloaded.
+ */
+static void __exit fsl_hypervisor_exit(void)
+{
+	struct doorbell_isr *dbisr, *n;
+
+	list_for_each_entry_safe(dbisr, n, &isr_list, list) {
+		free_irq(dbisr->irq, dbisr);
+		list_del(&dbisr->list);
+		kfree(dbisr);
+	}
+
+	misc_deregister(&fsl_hv_misc_dev);
+}
+
+module_init(fsl_hypervisor_init);
+module_exit(fsl_hypervisor_exit);
+
+MODULE_AUTHOR("Timur Tabi <timur@freescale.com>");
+MODULE_DESCRIPTION("Freescale hypervisor management driver");
+MODULE_LICENSE("GPL v2");

linux-7.2.3/drivers/virt/nitro_enclaves/Kconfig

@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+
+# Amazon Nitro Enclaves (NE) support.
+# Nitro is a hypervisor that has been developed by Amazon.
+
+config NITRO_ENCLAVES
+	tristate "Nitro Enclaves Support"
+	depends on (ARM64 || X86) && HOTPLUG_CPU && PCI && SMP
+	help
+	  This driver consists of support for enclave lifetime management
+	  for Nitro Enclaves (NE).
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called nitro_enclaves.
+
+config NITRO_ENCLAVES_MISC_DEV_TEST
+	bool "Tests for the misc device functionality of the Nitro Enclaves" if !KUNIT_ALL_TESTS
+	depends on NITRO_ENCLAVES && KUNIT=y
+	default KUNIT_ALL_TESTS
+	help
+	  Enable KUnit tests for the misc device functionality of the Nitro
+	  Enclaves. Select this option only if you will boot the kernel for
+	  the purpose of running unit tests (e.g. under UML or qemu). If
+	  unsure, say N.

linux-7.2.3/drivers/virt/nitro_enclaves/Makefile

@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+
+# Enclave lifetime management support for Nitro Enclaves (NE).
+
+obj-$(CONFIG_NITRO_ENCLAVES) += nitro_enclaves.o
+
+nitro_enclaves-y := ne_pci_dev.o ne_misc_dev.o

linux-7.2.3/drivers/virt/nitro_enclaves/ne_misc_dev.h

@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef _NE_MISC_DEV_H_
+#define _NE_MISC_DEV_H_
+
+#include <linux/cpumask.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/wait.h>
+
+#include "ne_pci_dev.h"
+
+/**
+ * struct ne_mem_region - Entry in the enclave user space memory regions list.
+ * @mem_region_list_entry:	Entry in the list of enclave memory regions.
+ * @memory_size:		Size of the user space memory region.
+ * @nr_pages:			Number of pages that make up the memory region.
+ * @pages:			Pages that make up the user space memory region.
+ * @userspace_addr:		User space address of the memory region.
+ */
+struct ne_mem_region {
+	struct list_head	mem_region_list_entry;
+	u64			memory_size;
+	unsigned long		nr_pages;
+	struct page		**pages;
+	u64			userspace_addr;
+};
+
+/**
+ * struct ne_enclave - Per-enclave data used for enclave lifetime management.
+ * @enclave_info_mutex :	Mutex for accessing this internal state.
+ * @enclave_list_entry :	Entry in the list of created enclaves.
+ * @eventq:			Wait queue used for out-of-band event notifications
+ *				triggered from the PCI device event handler to
+ *				the enclave process via the poll function.
+ * @has_event:			Variable used to determine if the out-of-band event
+ *				was triggered.
+ * @max_mem_regions:		The maximum number of memory regions that can be
+ *				handled by the hypervisor.
+ * @mem_regions_list:		Enclave user space memory regions list.
+ * @mem_size:			Enclave memory size.
+ * @mm :			Enclave process abstraction mm data struct.
+ * @nr_mem_regions:		Number of memory regions associated with the enclave.
+ * @nr_parent_vm_cores :	The size of the threads per core array. The
+ *				total number of CPU cores available on the
+ *				parent / primary VM.
+ * @nr_threads_per_core:	The number of threads that a full CPU core has.
+ * @nr_vcpus:			Number of vcpus associated with the enclave.
+ * @numa_node:			NUMA node of the enclave memory and CPUs.
+ * @slot_uid:			Slot unique id mapped to the enclave.
+ * @state:			Enclave state, updated during enclave lifetime.
+ * @threads_per_core:		Enclave full CPU cores array, indexed by core id,
+ *				consisting of cpumasks with all their threads.
+ *				Full CPU cores are taken from the NE CPU pool
+ *				and are available to the enclave.
+ * @vcpu_ids:			Cpumask of the vCPUs that are set for the enclave.
+ */
+struct ne_enclave {
+	struct mutex		enclave_info_mutex;
+	struct list_head	enclave_list_entry;
+	wait_queue_head_t	eventq;
+	bool			has_event;
+	u64			max_mem_regions;
+	struct list_head	mem_regions_list;
+	u64			mem_size;
+	struct mm_struct	*mm;
+	unsigned int		nr_mem_regions;
+	unsigned int		nr_parent_vm_cores;
+	unsigned int		nr_threads_per_core;
+	unsigned int		nr_vcpus;
+	int			numa_node;
+	u64			slot_uid;
+	u16			state;
+	cpumask_var_t		*threads_per_core;
+	cpumask_var_t		vcpu_ids;
+};
+
+/**
+ * enum ne_state - States available for an enclave.
+ * @NE_STATE_INIT:	The enclave has not been started yet.
+ * @NE_STATE_RUNNING:	The enclave was started and is running as expected.
+ * @NE_STATE_STOPPED:	The enclave exited without userspace interaction.
+ */
+enum ne_state {
+	NE_STATE_INIT		= 0,
+	NE_STATE_RUNNING	= 2,
+	NE_STATE_STOPPED	= U16_MAX,
+};
+
+/**
+ * struct ne_devs - Data structure to keep refs to the NE misc and PCI devices.
+ * @ne_misc_dev:	Nitro Enclaves misc device.
+ * @ne_pci_dev :	Nitro Enclaves PCI device.
+ */
+struct ne_devs {
+	struct miscdevice	*ne_misc_dev;
+	struct ne_pci_dev	*ne_pci_dev;
+};
+
+/* Nitro Enclaves (NE) data structure for keeping refs to the NE misc and PCI devices. */
+extern struct ne_devs ne_devs;
+
+#endif /* _NE_MISC_DEV_H_ */

linux-7.2.3/drivers/virt/nitro_enclaves/ne_misc_dev_test.c

@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <kunit/test.h>
+
+#define MAX_PHYS_REGIONS	16
+#define INVALID_VALUE		(~0ull)
+
+struct ne_phys_regions_test {
+	u64           paddr;
+	u64           size;
+	int           expect_rc;
+	unsigned long expect_num;
+	u64           expect_last_paddr;
+	u64           expect_last_size;
+} phys_regions_test_cases[] = {
+	/*
+	 * Add the region from 0x1000 to (0x1000 + 0x200000 - 1):
+	 *   Expected result:
+	 *       Failed, start address is not 2M-aligned
+	 *
+	 * Now the instance of struct ne_phys_contig_mem_regions is:
+	 *   num = 0
+	 *   regions = {}
+	 */
+	{0x1000, 0x200000, -EINVAL, 0, INVALID_VALUE, INVALID_VALUE},
+
+	/*
+	 * Add the region from 0x200000 to (0x200000 + 0x1000 - 1):
+	 *   Expected result:
+	 *       Failed, size is not 2M-aligned
+	 *
+	 * Now the instance of struct ne_phys_contig_mem_regions is:
+	 *   num = 0
+	 *   regions = {}
+	 */
+	{0x200000, 0x1000, -EINVAL, 0, INVALID_VALUE, INVALID_VALUE},
+
+	/*
+	 * Add the region from 0x200000 to (0x200000 + 0x200000 - 1):
+	 *   Expected result:
+	 *       Successful
+	 *
+	 * Now the instance of struct ne_phys_contig_mem_regions is:
+	 *   num = 1
+	 *   regions = {
+	 *       {start=0x200000, end=0x3fffff}, // len=0x200000
+	 *   }
+	 */
+	{0x200000, 0x200000, 0, 1, 0x200000, 0x200000},
+
+	/*
+	 * Add the region from 0x0 to (0x0 + 0x200000 - 1):
+	 *   Expected result:
+	 *       Successful
+	 *
+	 * Now the instance of struct ne_phys_contig_mem_regions is:
+	 *   num = 2
+	 *   regions = {
+	 *       {start=0x200000, end=0x3fffff}, // len=0x200000
+	 *       {start=0x0,      end=0x1fffff}, // len=0x200000
+	 *   }
+	 */
+	{0x0, 0x200000, 0, 2, 0x0, 0x200000},
+
+	/*
+	 * Add the region from 0x600000 to (0x600000 + 0x400000 - 1):
+	 *   Expected result:
+	 *       Successful
+	 *
+	 * Now the instance of struct ne_phys_contig_mem_regions is:
+	 *   num = 3
+	 *   regions = {
+	 *       {start=0x200000, end=0x3fffff}, // len=0x200000
+	 *       {start=0x0,      end=0x1fffff}, // len=0x200000
+	 *       {start=0x600000, end=0x9fffff}, // len=0x400000
+	 *   }
+	 */
+	{0x600000, 0x400000, 0, 3, 0x600000, 0x400000},
+
+	/*
+	 * Add the region from 0xa00000 to (0xa00000 + 0x400000 - 1):
+	 *   Expected result:
+	 *       Successful, merging case!
+	 *
+	 * Now the instance of struct ne_phys_contig_mem_regions is:
+	 *   num = 3
+	 *   regions = {
+	 *       {start=0x200000, end=0x3fffff}, // len=0x200000
+	 *       {start=0x0,      end=0x1fffff}, // len=0x200000
+	 *       {start=0x600000, end=0xdfffff}, // len=0x800000
+	 *   }
+	 */
+	{0xa00000, 0x400000, 0, 3, 0x600000, 0x800000},
+
+	/*
+	 * Add the region from 0x1000 to (0x1000 + 0x200000 - 1):
+	 *   Expected result:
+	 *       Failed, start address is not 2M-aligned
+	 *
+	 * Now the instance of struct ne_phys_contig_mem_regions is:
+	 *   num = 3
+	 *   regions = {
+	 *       {start=0x200000, end=0x3fffff}, // len=0x200000
+	 *       {start=0x0,      end=0x1fffff}, // len=0x200000
+	 *       {start=0x600000, end=0xdfffff}, // len=0x800000
+	 *   }
+	 */
+	{0x1000, 0x200000, -EINVAL, 3, 0x600000, 0x800000},
+};
+
+static void ne_misc_dev_test_merge_phys_contig_memory_regions(struct kunit *test)
+{
+	struct ne_phys_contig_mem_regions phys_contig_mem_regions = {};
+	int rc = 0;
+	int i = 0;
+
+	phys_contig_mem_regions.regions = kunit_kcalloc(test, MAX_PHYS_REGIONS,
+							sizeof(*phys_contig_mem_regions.regions),
+							GFP_KERNEL);
+	KUNIT_ASSERT_TRUE(test, phys_contig_mem_regions.regions);
+
+	for (i = 0; i < ARRAY_SIZE(phys_regions_test_cases); i++) {
+		struct ne_phys_regions_test *test_case = &phys_regions_test_cases[i];
+		unsigned long num = 0;
+
+		rc = ne_merge_phys_contig_memory_regions(&phys_contig_mem_regions,
+							 test_case->paddr, test_case->size);
+		KUNIT_EXPECT_EQ(test, rc, test_case->expect_rc);
+		KUNIT_EXPECT_EQ(test, phys_contig_mem_regions.num, test_case->expect_num);
+
+		if (test_case->expect_last_paddr == INVALID_VALUE)
+			continue;
+
+		num = phys_contig_mem_regions.num;
+		KUNIT_EXPECT_EQ(test, phys_contig_mem_regions.regions[num - 1].start,
+				test_case->expect_last_paddr);
+		KUNIT_EXPECT_EQ(test, range_len(&phys_contig_mem_regions.regions[num - 1]),
+				test_case->expect_last_size);
+	}
+
+	kunit_kfree(test, phys_contig_mem_regions.regions);
+}
+
+static struct kunit_case ne_misc_dev_test_cases[] = {
+	KUNIT_CASE(ne_misc_dev_test_merge_phys_contig_memory_regions),
+	{}
+};
+
+static struct kunit_suite ne_misc_dev_test_suite = {
+	.name = "ne_misc_dev_test",
+	.test_cases = ne_misc_dev_test_cases,
+};
+
+kunit_test_suite(ne_misc_dev_test_suite);

linux-7.2.3/drivers/virt/nitro_enclaves/ne_pci_dev.c

@@ -0,0 +1,626 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+/**
+ * DOC: Nitro Enclaves (NE) PCI device driver.
+ */
+
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/nitro_enclaves.h>
+#include <linux/pci.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#include "ne_misc_dev.h"
+#include "ne_pci_dev.h"
+
+/**
+ * NE_DEFAULT_TIMEOUT_MSECS - Default timeout to wait for a reply from
+ *			      the NE PCI device.
+ */
+#define NE_DEFAULT_TIMEOUT_MSECS	(120000) /* 120 sec */
+
+static const struct pci_device_id ne_pci_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMAZON, PCI_DEVICE_ID_NE) },
+	{ 0, }
+};
+
+MODULE_DEVICE_TABLE(pci, ne_pci_ids);
+
+/**
+ * ne_submit_request() - Submit command request to the PCI device based on the
+ *			 command type.
+ * @pdev:		PCI device to send the command to.
+ * @cmd_type:		Command type of the request sent to the PCI device.
+ * @cmd_request:	Command request payload.
+ * @cmd_request_size:	Size of the command request payload.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev mutex held.
+ */
+static void ne_submit_request(struct pci_dev *pdev, enum ne_pci_dev_cmd_type cmd_type,
+			      void *cmd_request, size_t cmd_request_size)
+{
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+	memcpy_toio(ne_pci_dev->iomem_base + NE_SEND_DATA, cmd_request, cmd_request_size);
+
+	iowrite32(cmd_type, ne_pci_dev->iomem_base + NE_COMMAND);
+}
+
+/**
+ * ne_retrieve_reply() - Retrieve reply from the PCI device.
+ * @pdev:		PCI device to receive the reply from.
+ * @cmd_reply:		Command reply payload.
+ * @cmd_reply_size:	Size of the command reply payload.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev mutex held.
+ */
+static void ne_retrieve_reply(struct pci_dev *pdev, struct ne_pci_dev_cmd_reply *cmd_reply,
+			      size_t cmd_reply_size)
+{
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+	memcpy_fromio(cmd_reply, ne_pci_dev->iomem_base + NE_RECV_DATA, cmd_reply_size);
+}
+
+/**
+ * ne_wait_for_reply() - Wait for a reply of a PCI device command.
+ * @pdev:	PCI device for which a reply is waited.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_wait_for_reply(struct pci_dev *pdev)
+{
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+	int rc = -EINVAL;
+
+	/*
+	 * TODO: Update to _interruptible and handle interrupted wait event
+	 * e.g. -ERESTARTSYS, incoming signals + update timeout, if needed.
+	 */
+	rc = wait_event_timeout(ne_pci_dev->cmd_reply_wait_q,
+				atomic_read(&ne_pci_dev->cmd_reply_avail) != 0,
+				msecs_to_jiffies(NE_DEFAULT_TIMEOUT_MSECS));
+	if (!rc)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+int ne_do_request(struct pci_dev *pdev, enum ne_pci_dev_cmd_type cmd_type,
+		  void *cmd_request, size_t cmd_request_size,
+		  struct ne_pci_dev_cmd_reply *cmd_reply, size_t cmd_reply_size)
+{
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+	int rc = -EINVAL;
+
+	if (cmd_type <= INVALID_CMD || cmd_type >= MAX_CMD) {
+		dev_err_ratelimited(&pdev->dev, "Invalid cmd type=%u\n", cmd_type);
+
+		return -EINVAL;
+	}
+
+	if (!cmd_request) {
+		dev_err_ratelimited(&pdev->dev, "Null cmd request for cmd type=%u\n",
+				    cmd_type);
+
+		return -EINVAL;
+	}
+
+	if (cmd_request_size > NE_SEND_DATA_SIZE) {
+		dev_err_ratelimited(&pdev->dev, "Invalid req size=%zu for cmd type=%u\n",
+				    cmd_request_size, cmd_type);
+
+		return -EINVAL;
+	}
+
+	if (!cmd_reply) {
+		dev_err_ratelimited(&pdev->dev, "Null cmd reply for cmd type=%u\n",
+				    cmd_type);
+
+		return -EINVAL;
+	}
+
+	if (cmd_reply_size > NE_RECV_DATA_SIZE) {
+		dev_err_ratelimited(&pdev->dev, "Invalid reply size=%zu for cmd type=%u\n",
+				    cmd_reply_size, cmd_type);
+
+		return -EINVAL;
+	}
+
+	/*
+	 * Use this mutex so that the PCI device handles one command request at
+	 * a time.
+	 */
+	mutex_lock(&ne_pci_dev->pci_dev_mutex);
+
+	atomic_set(&ne_pci_dev->cmd_reply_avail, 0);
+
+	ne_submit_request(pdev, cmd_type, cmd_request, cmd_request_size);
+
+	rc = ne_wait_for_reply(pdev);
+	if (rc < 0) {
+		dev_err_ratelimited(&pdev->dev, "Error in wait for reply for cmd type=%u [rc=%d]\n",
+				    cmd_type, rc);
+
+		goto unlock_mutex;
+	}
+
+	ne_retrieve_reply(pdev, cmd_reply, cmd_reply_size);
+
+	atomic_set(&ne_pci_dev->cmd_reply_avail, 0);
+
+	if (cmd_reply->rc < 0) {
+		rc = cmd_reply->rc;
+
+		dev_err_ratelimited(&pdev->dev, "Error in cmd process logic, cmd type=%u [rc=%d]\n",
+				    cmd_type, rc);
+
+		goto unlock_mutex;
+	}
+
+	rc = 0;
+
+unlock_mutex:
+	mutex_unlock(&ne_pci_dev->pci_dev_mutex);
+
+	return rc;
+}
+
+/**
+ * ne_reply_handler() - Interrupt handler for retrieving a reply matching a
+ *			request sent to the PCI device for enclave lifetime
+ *			management.
+ * @irq:	Received interrupt for a reply sent by the PCI device.
+ * @args:	PCI device private data structure.
+ *
+ * Context: Interrupt context.
+ * Return:
+ * * IRQ_HANDLED on handled interrupt.
+ */
+static irqreturn_t ne_reply_handler(int irq, void *args)
+{
+	struct ne_pci_dev *ne_pci_dev = (struct ne_pci_dev *)args;
+
+	atomic_set(&ne_pci_dev->cmd_reply_avail, 1);
+
+	/* TODO: Update to _interruptible. */
+	wake_up(&ne_pci_dev->cmd_reply_wait_q);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ne_event_work_handler() - Work queue handler for notifying enclaves on a
+ *			     state change received by the event interrupt
+ *			     handler.
+ * @work:	Item containing the NE PCI device for which an out-of-band event
+ *		was issued.
+ *
+ * An out-of-band event is being issued by the Nitro Hypervisor when at least
+ * one enclave is changing state without client interaction.
+ *
+ * Context: Work queue context.
+ */
+static void ne_event_work_handler(struct work_struct *work)
+{
+	struct ne_pci_dev_cmd_reply cmd_reply = {};
+	struct ne_enclave *ne_enclave = NULL;
+	struct ne_pci_dev *ne_pci_dev =
+		container_of(work, struct ne_pci_dev, notify_work);
+	struct pci_dev *pdev = ne_pci_dev->pdev;
+	int rc = -EINVAL;
+	struct slot_info_req slot_info_req = {};
+
+	mutex_lock(&ne_pci_dev->enclaves_list_mutex);
+
+	/*
+	 * Iterate over all enclaves registered for the Nitro Enclaves
+	 * PCI device and determine for which enclave(s) the out-of-band event
+	 * is corresponding to.
+	 */
+	list_for_each_entry(ne_enclave, &ne_pci_dev->enclaves_list, enclave_list_entry) {
+		mutex_lock(&ne_enclave->enclave_info_mutex);
+
+		/*
+		 * Enclaves that were never started cannot receive out-of-band
+		 * events.
+		 */
+		if (ne_enclave->state != NE_STATE_RUNNING)
+			goto unlock;
+
+		slot_info_req.slot_uid = ne_enclave->slot_uid;
+
+		rc = ne_do_request(pdev, SLOT_INFO,
+				   &slot_info_req, sizeof(slot_info_req),
+				   &cmd_reply, sizeof(cmd_reply));
+		if (rc < 0)
+			dev_err(&pdev->dev, "Error in slot info [rc=%d]\n", rc);
+
+		/* Notify enclave process that the enclave state changed. */
+		if (ne_enclave->state != cmd_reply.state) {
+			ne_enclave->state = cmd_reply.state;
+
+			ne_enclave->has_event = true;
+
+			wake_up_interruptible(&ne_enclave->eventq);
+		}
+
+unlock:
+		 mutex_unlock(&ne_enclave->enclave_info_mutex);
+	}
+
+	mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+}
+
+/**
+ * ne_event_handler() - Interrupt handler for PCI device out-of-band events.
+ *			This interrupt does not supply any data in the MMIO
+ *			region. It notifies a change in the state of any of
+ *			the launched enclaves.
+ * @irq:	Received interrupt for an out-of-band event.
+ * @args:	PCI device private data structure.
+ *
+ * Context: Interrupt context.
+ * Return:
+ * * IRQ_HANDLED on handled interrupt.
+ */
+static irqreturn_t ne_event_handler(int irq, void *args)
+{
+	struct ne_pci_dev *ne_pci_dev = (struct ne_pci_dev *)args;
+
+	queue_work(ne_pci_dev->event_wq, &ne_pci_dev->notify_work);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ne_setup_msix() - Setup MSI-X vectors for the PCI device.
+ * @pdev:	PCI device to setup the MSI-X for.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_setup_msix(struct pci_dev *pdev)
+{
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+	int nr_vecs = 0;
+	int rc = -EINVAL;
+
+	nr_vecs = pci_msix_vec_count(pdev);
+	if (nr_vecs < 0) {
+		rc = nr_vecs;
+
+		dev_err(&pdev->dev, "Error in getting vec count [rc=%d]\n", rc);
+
+		return rc;
+	}
+
+	rc = pci_alloc_irq_vectors(pdev, nr_vecs, nr_vecs, PCI_IRQ_MSIX);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "Error in alloc MSI-X vecs [rc=%d]\n", rc);
+
+		return rc;
+	}
+
+	/*
+	 * This IRQ gets triggered every time the PCI device responds to a
+	 * command request. The reply is then retrieved, reading from the MMIO
+	 * space of the PCI device.
+	 */
+	rc = request_irq(pci_irq_vector(pdev, NE_VEC_REPLY), ne_reply_handler,
+			 0, "enclave_cmd", ne_pci_dev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "Error in request irq reply [rc=%d]\n", rc);
+
+		goto free_irq_vectors;
+	}
+
+	ne_pci_dev->event_wq = create_singlethread_workqueue("ne_pci_dev_wq");
+	if (!ne_pci_dev->event_wq) {
+		rc = -ENOMEM;
+
+		dev_err(&pdev->dev, "Cannot get wq for dev events [rc=%d]\n", rc);
+
+		goto free_reply_irq_vec;
+	}
+
+	INIT_WORK(&ne_pci_dev->notify_work, ne_event_work_handler);
+
+	/*
+	 * This IRQ gets triggered every time any enclave's state changes. Its
+	 * handler then scans for the changes and propagates them to the user
+	 * space.
+	 */
+	rc = request_irq(pci_irq_vector(pdev, NE_VEC_EVENT), ne_event_handler,
+			 0, "enclave_evt", ne_pci_dev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "Error in request irq event [rc=%d]\n", rc);
+
+		goto destroy_wq;
+	}
+
+	return 0;
+
+destroy_wq:
+	destroy_workqueue(ne_pci_dev->event_wq);
+free_reply_irq_vec:
+	free_irq(pci_irq_vector(pdev, NE_VEC_REPLY), ne_pci_dev);
+free_irq_vectors:
+	pci_free_irq_vectors(pdev);
+
+	return rc;
+}
+
+/**
+ * ne_teardown_msix() - Teardown MSI-X vectors for the PCI device.
+ * @pdev:	PCI device to teardown the MSI-X for.
+ *
+ * Context: Process context.
+ */
+static void ne_teardown_msix(struct pci_dev *pdev)
+{
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+	free_irq(pci_irq_vector(pdev, NE_VEC_EVENT), ne_pci_dev);
+
+	flush_work(&ne_pci_dev->notify_work);
+	destroy_workqueue(ne_pci_dev->event_wq);
+
+	free_irq(pci_irq_vector(pdev, NE_VEC_REPLY), ne_pci_dev);
+
+	pci_free_irq_vectors(pdev);
+}
+
+/**
+ * ne_pci_dev_enable() - Select the PCI device version and enable it.
+ * @pdev:	PCI device to select version for and then enable.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_pci_dev_enable(struct pci_dev *pdev)
+{
+	u8 dev_enable_reply = 0;
+	u16 dev_version_reply = 0;
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+	iowrite16(NE_VERSION_MAX, ne_pci_dev->iomem_base + NE_VERSION);
+
+	dev_version_reply = ioread16(ne_pci_dev->iomem_base + NE_VERSION);
+	if (dev_version_reply != NE_VERSION_MAX) {
+		dev_err(&pdev->dev, "Error in pci dev version cmd\n");
+
+		return -EIO;
+	}
+
+	iowrite8(NE_ENABLE_ON, ne_pci_dev->iomem_base + NE_ENABLE);
+
+	dev_enable_reply = ioread8(ne_pci_dev->iomem_base + NE_ENABLE);
+	if (dev_enable_reply != NE_ENABLE_ON) {
+		dev_err(&pdev->dev, "Error in pci dev enable cmd\n");
+
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * ne_pci_dev_disable() - Disable the PCI device.
+ * @pdev:	PCI device to disable.
+ *
+ * Context: Process context.
+ */
+static void ne_pci_dev_disable(struct pci_dev *pdev)
+{
+	u8 dev_disable_reply = 0;
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+	const unsigned int sleep_time = 10; /* 10 ms */
+	unsigned int sleep_time_count = 0;
+
+	iowrite8(NE_ENABLE_OFF, ne_pci_dev->iomem_base + NE_ENABLE);
+
+	/*
+	 * Check for NE_ENABLE_OFF in a loop, to handle cases when the device
+	 * state is not immediately set to disabled and going through a
+	 * transitory state of disabling.
+	 */
+	while (sleep_time_count < NE_DEFAULT_TIMEOUT_MSECS) {
+		dev_disable_reply = ioread8(ne_pci_dev->iomem_base + NE_ENABLE);
+		if (dev_disable_reply == NE_ENABLE_OFF)
+			return;
+
+		msleep_interruptible(sleep_time);
+		sleep_time_count += sleep_time;
+	}
+
+	dev_disable_reply = ioread8(ne_pci_dev->iomem_base + NE_ENABLE);
+	if (dev_disable_reply != NE_ENABLE_OFF)
+		dev_err(&pdev->dev, "Error in pci dev disable cmd\n");
+}
+
+/**
+ * ne_pci_probe() - Probe function for the NE PCI device.
+ * @pdev:	PCI device to match with the NE PCI driver.
+ * @id :	PCI device id table associated with the NE PCI driver.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct ne_pci_dev *ne_pci_dev = NULL;
+	int rc = -EINVAL;
+
+	ne_pci_dev = kzalloc_obj(*ne_pci_dev);
+	if (!ne_pci_dev)
+		return -ENOMEM;
+
+	rc = pci_enable_device(pdev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "Error in pci dev enable [rc=%d]\n", rc);
+
+		goto free_ne_pci_dev;
+	}
+
+	pci_set_master(pdev);
+
+	rc = pci_request_regions_exclusive(pdev, "nitro_enclaves");
+	if (rc < 0) {
+		dev_err(&pdev->dev, "Error in pci request regions [rc=%d]\n", rc);
+
+		goto disable_pci_dev;
+	}
+
+	ne_pci_dev->iomem_base = pci_iomap(pdev, PCI_BAR_NE, 0);
+	if (!ne_pci_dev->iomem_base) {
+		rc = -ENOMEM;
+
+		dev_err(&pdev->dev, "Error in pci iomap [rc=%d]\n", rc);
+
+		goto release_pci_regions;
+	}
+
+	pci_set_drvdata(pdev, ne_pci_dev);
+
+	rc = ne_setup_msix(pdev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "Error in pci dev msix setup [rc=%d]\n", rc);
+
+		goto iounmap_pci_bar;
+	}
+
+	ne_pci_dev_disable(pdev);
+
+	rc = ne_pci_dev_enable(pdev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "Error in ne_pci_dev enable [rc=%d]\n", rc);
+
+		goto teardown_msix;
+	}
+
+	atomic_set(&ne_pci_dev->cmd_reply_avail, 0);
+	init_waitqueue_head(&ne_pci_dev->cmd_reply_wait_q);
+	INIT_LIST_HEAD(&ne_pci_dev->enclaves_list);
+	mutex_init(&ne_pci_dev->enclaves_list_mutex);
+	mutex_init(&ne_pci_dev->pci_dev_mutex);
+	ne_pci_dev->pdev = pdev;
+
+	ne_devs.ne_pci_dev = ne_pci_dev;
+
+	rc = misc_register(ne_devs.ne_misc_dev);
+	if (rc < 0) {
+		dev_err(&pdev->dev, "Error in misc dev register [rc=%d]\n", rc);
+
+		goto disable_ne_pci_dev;
+	}
+
+	return 0;
+
+disable_ne_pci_dev:
+	ne_devs.ne_pci_dev = NULL;
+	ne_pci_dev_disable(pdev);
+teardown_msix:
+	ne_teardown_msix(pdev);
+iounmap_pci_bar:
+	pci_set_drvdata(pdev, NULL);
+	pci_iounmap(pdev, ne_pci_dev->iomem_base);
+release_pci_regions:
+	pci_release_regions(pdev);
+disable_pci_dev:
+	pci_disable_device(pdev);
+free_ne_pci_dev:
+	kfree(ne_pci_dev);
+
+	return rc;
+}
+
+/**
+ * ne_pci_remove() - Remove function for the NE PCI device.
+ * @pdev:	PCI device associated with the NE PCI driver.
+ *
+ * Context: Process context.
+ */
+static void ne_pci_remove(struct pci_dev *pdev)
+{
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+	misc_deregister(ne_devs.ne_misc_dev);
+
+	ne_devs.ne_pci_dev = NULL;
+
+	ne_pci_dev_disable(pdev);
+
+	ne_teardown_msix(pdev);
+
+	pci_set_drvdata(pdev, NULL);
+
+	pci_iounmap(pdev, ne_pci_dev->iomem_base);
+
+	pci_release_regions(pdev);
+
+	pci_disable_device(pdev);
+
+	kfree(ne_pci_dev);
+}
+
+/**
+ * ne_pci_shutdown() - Shutdown function for the NE PCI device.
+ * @pdev:	PCI device associated with the NE PCI driver.
+ *
+ * Context: Process context.
+ */
+static void ne_pci_shutdown(struct pci_dev *pdev)
+{
+	struct ne_pci_dev *ne_pci_dev = pci_get_drvdata(pdev);
+
+	if (!ne_pci_dev)
+		return;
+
+	misc_deregister(ne_devs.ne_misc_dev);
+
+	ne_devs.ne_pci_dev = NULL;
+
+	ne_pci_dev_disable(pdev);
+
+	ne_teardown_msix(pdev);
+
+	pci_set_drvdata(pdev, NULL);
+
+	pci_iounmap(pdev, ne_pci_dev->iomem_base);
+
+	pci_release_regions(pdev);
+
+	pci_disable_device(pdev);
+
+	kfree(ne_pci_dev);
+}
+
+/*
+ * TODO: Add suspend / resume functions for power management w/ CONFIG_PM, if
+ * needed.
+ */
+/* NE PCI device driver. */
+struct pci_driver ne_pci_driver = {
+	.name		= "nitro_enclaves",
+	.id_table	= ne_pci_ids,
+	.probe		= ne_pci_probe,
+	.remove		= ne_pci_remove,
+	.shutdown	= ne_pci_shutdown,
+};

linux-7.2.3/drivers/virt/nitro_enclaves/ne_pci_dev.h

@@ -0,0 +1,331 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+#ifndef _NE_PCI_DEV_H_
+#define _NE_PCI_DEV_H_
+
+#include <linux/atomic.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/wait.h>
+
+/**
+ * DOC: Nitro Enclaves (NE) PCI device
+ */
+
+/**
+ * PCI_DEVICE_ID_NE - Nitro Enclaves PCI device id.
+ */
+#define PCI_DEVICE_ID_NE	(0xe4c1)
+/**
+ * PCI_BAR_NE - Nitro Enclaves PCI device MMIO BAR.
+ */
+#define PCI_BAR_NE		(0x03)
+
+/**
+ * DOC: Device registers in the NE PCI device MMIO BAR
+ */
+
+/**
+ * NE_ENABLE - (1 byte) Register to notify the device that the driver is using
+ *	       it (Read/Write).
+ */
+#define NE_ENABLE		(0x0000)
+#define NE_ENABLE_OFF		(0x00)
+#define NE_ENABLE_ON		(0x01)
+
+/**
+ * NE_VERSION - (2 bytes) Register to select the device run-time version
+ *		(Read/Write).
+ */
+#define NE_VERSION		(0x0002)
+#define NE_VERSION_MAX		(0x0001)
+
+/**
+ * NE_COMMAND - (4 bytes) Register to notify the device what command was
+ *		requested (Write-Only).
+ */
+#define NE_COMMAND		(0x0004)
+
+/**
+ * NE_EVTCNT - (4 bytes) Register to notify the driver that a reply or a device
+ *	       event is available (Read-Only):
+ *	       - Lower half  - command reply counter
+ *	       - Higher half - out-of-band device event counter
+ */
+#define NE_EVTCNT		(0x000c)
+#define NE_EVTCNT_REPLY_SHIFT	(0)
+#define NE_EVTCNT_REPLY_MASK	(0x0000ffff)
+#define NE_EVTCNT_REPLY(cnt)	(((cnt) & NE_EVTCNT_REPLY_MASK) >> \
+				NE_EVTCNT_REPLY_SHIFT)
+#define NE_EVTCNT_EVENT_SHIFT	(16)
+#define NE_EVTCNT_EVENT_MASK	(0xffff0000)
+#define NE_EVTCNT_EVENT(cnt)	(((cnt) & NE_EVTCNT_EVENT_MASK) >> \
+				NE_EVTCNT_EVENT_SHIFT)
+
+/**
+ * NE_SEND_DATA - (240 bytes) Buffer for sending the command request payload
+ *		  (Read/Write).
+ */
+#define NE_SEND_DATA		(0x0010)
+
+/**
+ * NE_RECV_DATA - (240 bytes) Buffer for receiving the command reply payload
+ *		  (Read-Only).
+ */
+#define NE_RECV_DATA		(0x0100)
+
+/**
+ * DOC: Device MMIO buffer sizes
+ */
+
+/**
+ * NE_SEND_DATA_SIZE - Size of the send buffer, in bytes.
+ */
+#define NE_SEND_DATA_SIZE	(240)
+
+/**
+ * NE_RECV_DATA_SIZE - Size of the receive buffer, in bytes.
+ */
+#define NE_RECV_DATA_SIZE	(240)
+
+/**
+ * DOC: MSI-X interrupt vectors
+ */
+
+/**
+ * NE_VEC_REPLY - MSI-X vector used for command reply notification.
+ */
+#define NE_VEC_REPLY		(0)
+
+/**
+ * NE_VEC_EVENT - MSI-X vector used for out-of-band events e.g. enclave crash.
+ */
+#define NE_VEC_EVENT		(1)
+
+/**
+ * enum ne_pci_dev_cmd_type - Device command types.
+ * @INVALID_CMD:		Invalid command.
+ * @ENCLAVE_START:		Start an enclave, after setting its resources.
+ * @ENCLAVE_GET_SLOT:		Get the slot uid of an enclave.
+ * @ENCLAVE_STOP:		Terminate an enclave.
+ * @SLOT_ALLOC :		Allocate a slot for an enclave.
+ * @SLOT_FREE:			Free the slot allocated for an enclave
+ * @SLOT_ADD_MEM:		Add a memory region to an enclave slot.
+ * @SLOT_ADD_VCPU:		Add a vCPU to an enclave slot.
+ * @SLOT_COUNT :		Get the number of allocated slots.
+ * @NEXT_SLOT:			Get the next slot in the list of allocated slots.
+ * @SLOT_INFO:			Get the info for a slot e.g. slot uid, vCPUs count.
+ * @SLOT_ADD_BULK_VCPUS:	Add a number of vCPUs, not providing CPU ids.
+ * @MAX_CMD:			A gatekeeper for max possible command type.
+ */
+enum ne_pci_dev_cmd_type {
+	INVALID_CMD		= 0,
+	ENCLAVE_START		= 1,
+	ENCLAVE_GET_SLOT	= 2,
+	ENCLAVE_STOP		= 3,
+	SLOT_ALLOC		= 4,
+	SLOT_FREE		= 5,
+	SLOT_ADD_MEM		= 6,
+	SLOT_ADD_VCPU		= 7,
+	SLOT_COUNT		= 8,
+	NEXT_SLOT		= 9,
+	SLOT_INFO		= 10,
+	SLOT_ADD_BULK_VCPUS	= 11,
+	MAX_CMD,
+};
+
+/**
+ * DOC: Device commands - payload structure for requests and replies.
+ */
+
+/**
+ * struct enclave_start_req - ENCLAVE_START request.
+ * @slot_uid:		Slot unique id mapped to the enclave to start.
+ * @enclave_cid:	Context ID (CID) for the enclave vsock device.
+ *			If 0, CID is autogenerated.
+ * @flags:		Flags for the enclave to start with (e.g. debug mode).
+ */
+struct enclave_start_req {
+	u64	slot_uid;
+	u64	enclave_cid;
+	u64	flags;
+};
+
+/**
+ * struct enclave_get_slot_req - ENCLAVE_GET_SLOT request.
+ * @enclave_cid:	Context ID (CID) for the enclave vsock device.
+ */
+struct enclave_get_slot_req {
+	u64	enclave_cid;
+};
+
+/**
+ * struct enclave_stop_req - ENCLAVE_STOP request.
+ * @slot_uid:	Slot unique id mapped to the enclave to stop.
+ */
+struct enclave_stop_req {
+	u64	slot_uid;
+};
+
+/**
+ * struct slot_alloc_req - SLOT_ALLOC request.
+ * @unused:	In order to avoid weird sizeof edge cases.
+ */
+struct slot_alloc_req {
+	u8	unused;
+};
+
+/**
+ * struct slot_free_req - SLOT_FREE request.
+ * @slot_uid:	Slot unique id mapped to the slot to free.
+ */
+struct slot_free_req {
+	u64	slot_uid;
+};
+
+/* TODO: Add flags field to the request to add memory region. */
+/**
+ * struct slot_add_mem_req - SLOT_ADD_MEM request.
+ * @slot_uid:	Slot unique id mapped to the slot to add the memory region to.
+ * @paddr:	Physical address of the memory region to add to the slot.
+ * @size:	Memory size, in bytes, of the memory region to add to the slot.
+ */
+struct slot_add_mem_req {
+	u64	slot_uid;
+	u64	paddr;
+	u64	size;
+};
+
+/**
+ * struct slot_add_vcpu_req - SLOT_ADD_VCPU request.
+ * @slot_uid:	Slot unique id mapped to the slot to add the vCPU to.
+ * @vcpu_id:	vCPU ID of the CPU to add to the enclave.
+ * @padding:	Padding for the overall data structure.
+ */
+struct slot_add_vcpu_req {
+	u64	slot_uid;
+	u32	vcpu_id;
+	u8	padding[4];
+};
+
+/**
+ * struct slot_count_req - SLOT_COUNT request.
+ * @unused:	In order to avoid weird sizeof edge cases.
+ */
+struct slot_count_req {
+	u8	unused;
+};
+
+/**
+ * struct next_slot_req - NEXT_SLOT request.
+ * @slot_uid:	Slot unique id of the next slot in the iteration.
+ */
+struct next_slot_req {
+	u64	slot_uid;
+};
+
+/**
+ * struct slot_info_req - SLOT_INFO request.
+ * @slot_uid:	Slot unique id mapped to the slot to get information about.
+ */
+struct slot_info_req {
+	u64	slot_uid;
+};
+
+/**
+ * struct slot_add_bulk_vcpus_req - SLOT_ADD_BULK_VCPUS request.
+ * @slot_uid:	Slot unique id mapped to the slot to add vCPUs to.
+ * @nr_vcpus:	Number of vCPUs to add to the slot.
+ */
+struct slot_add_bulk_vcpus_req {
+	u64	slot_uid;
+	u64	nr_vcpus;
+};
+
+/**
+ * struct ne_pci_dev_cmd_reply - NE PCI device command reply.
+ * @rc :		Return code of the logic that processed the request.
+ * @padding0:		Padding for the overall data structure.
+ * @slot_uid:		Valid for all commands except SLOT_COUNT.
+ * @enclave_cid:	Valid for ENCLAVE_START command.
+ * @slot_count :	Valid for SLOT_COUNT command.
+ * @mem_regions:	Valid for SLOT_ALLOC and SLOT_INFO commands.
+ * @mem_size:		Valid for SLOT_INFO command.
+ * @nr_vcpus:		Valid for SLOT_INFO command.
+ * @flags:		Valid for SLOT_INFO command.
+ * @state:		Valid for SLOT_INFO command.
+ * @padding1:		Padding for the overall data structure.
+ */
+struct ne_pci_dev_cmd_reply {
+	s32	rc;
+	u8	padding0[4];
+	u64	slot_uid;
+	u64	enclave_cid;
+	u64	slot_count;
+	u64	mem_regions;
+	u64	mem_size;
+	u64	nr_vcpus;
+	u64	flags;
+	u16	state;
+	u8	padding1[6];
+};
+
+/**
+ * struct ne_pci_dev - Nitro Enclaves (NE) PCI device.
+ * @cmd_reply_avail:		Variable set if a reply has been sent by the
+ *				PCI device.
+ * @cmd_reply_wait_q:		Wait queue for handling command reply from the
+ *				PCI device.
+ * @enclaves_list:		List of the enclaves managed by the PCI device.
+ * @enclaves_list_mutex:	Mutex for accessing the list of enclaves.
+ * @event_wq:			Work queue for handling out-of-band events
+ *				triggered by the Nitro Hypervisor which require
+ *				enclave state scanning and propagation to the
+ *				enclave process.
+ * @iomem_base :		MMIO region of the PCI device.
+ * @notify_work:		Work item for every received out-of-band event.
+ * @pci_dev_mutex:		Mutex for accessing the PCI device MMIO space.
+ * @pdev:			PCI device data structure.
+ */
+struct ne_pci_dev {
+	atomic_t		cmd_reply_avail;
+	wait_queue_head_t	cmd_reply_wait_q;
+	struct list_head	enclaves_list;
+	struct mutex		enclaves_list_mutex;
+	struct workqueue_struct	*event_wq;
+	void __iomem		*iomem_base;
+	struct work_struct	notify_work;
+	struct mutex		pci_dev_mutex;
+	struct pci_dev		*pdev;
+};
+
+/**
+ * ne_do_request() - Submit command request to the PCI device based on the command
+ *		     type and retrieve the associated reply.
+ * @pdev:		PCI device to send the command to and receive the reply from.
+ * @cmd_type:		Command type of the request sent to the PCI device.
+ * @cmd_request:	Command request payload.
+ * @cmd_request_size:	Size of the command request payload.
+ * @cmd_reply:		Command reply payload.
+ * @cmd_reply_size:	Size of the command reply payload.
+ *
+ * Context: Process context. This function uses the ne_pci_dev mutex to handle
+ *	    one command at a time.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+int ne_do_request(struct pci_dev *pdev, enum ne_pci_dev_cmd_type cmd_type,
+		  void *cmd_request, size_t cmd_request_size,
+		  struct ne_pci_dev_cmd_reply *cmd_reply,
+		  size_t cmd_reply_size);
+
+/* Nitro Enclaves (NE) PCI device driver */
+extern struct pci_driver ne_pci_driver;
+
+#endif /* _NE_PCI_DEV_H_ */

linux-7.2.3/drivers/virt/vboxguest/Kconfig

@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config VBOXGUEST
+	tristate "Virtual Box Guest integration support"
+	depends on (ARM64 || X86 || COMPILE_TEST) && PCI && INPUT
+	depends on HAS_IOPORT
+	help
+	  This is a driver for the Virtual Box Guest PCI device used in
+	  Virtual Box virtual machines. Enabling this driver will add
+	  support for Virtual Box Guest integration features such as
+	  copy-and-paste, seamless mode and OpenGL pass-through.
+
+	  This driver also offers vboxguest IPC functionality which is needed
+	  for the vboxfs driver which offers folder sharing support.
+
+	  If you enable this driver you should also enable the VBOXVIDEO option.
+
+	  Although it is possible to build this module in, it is advised
+	  to build this driver as a module, so that it can be updated
+	  independently of the kernel. Select M to build this driver as a
+	  module.

linux-7.2.3/drivers/virt/vboxguest/Makefile

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+vboxguest-y := vboxguest_linux.o vboxguest_core.o vboxguest_utils.o
+
+obj-$(CONFIG_VBOXGUEST) += vboxguest.o

linux-7.2.3/drivers/virt/vboxguest/vboxguest_core.h

@@ -0,0 +1,214 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */
+/* Copyright (C) 2010-2016 Oracle Corporation */
+
+#ifndef __VBOXGUEST_CORE_H__
+#define __VBOXGUEST_CORE_H__
+
+#include <linux/input.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include <linux/vboxguest.h>
+#include "vmmdev.h"
+
+/*
+ * The mainline kernel version (this version) of the vboxguest module
+ * contained a bug where it defined VBGL_IOCTL_VMMDEV_REQUEST_BIG and
+ * VBGL_IOCTL_LOG using _IOC(_IOC_READ | _IOC_WRITE, 'V', ...) instead
+ * of _IO(V, ...) as the out of tree VirtualBox upstream version does.
+ *
+ * These _ALT definitions keep compatibility with the wrong defines the
+ * mainline kernel version used for a while.
+ * Note the VirtualBox userspace bits have always been built against
+ * VirtualBox upstream's headers, so this is likely not necessary. But
+ * we must never break our ABI so we keep these around to be 100% sure.
+ */
+#define VBG_IOCTL_VMMDEV_REQUEST_BIG_ALT _IOC(_IOC_READ | _IOC_WRITE, 'V', 3, 0)
+#define VBG_IOCTL_LOG_ALT(s)             _IOC(_IOC_READ | _IOC_WRITE, 'V', 9, s)
+
+struct vbg_session;
+
+/** VBox guest memory balloon. */
+struct vbg_mem_balloon {
+	/** Work handling VMMDEV_EVENT_BALLOON_CHANGE_REQUEST events */
+	struct work_struct work;
+	/** Pre-allocated vmmdev_memballoon_info req for query */
+	struct vmmdev_memballoon_info *get_req;
+	/** Pre-allocated vmmdev_memballoon_change req for inflate / deflate */
+	struct vmmdev_memballoon_change *change_req;
+	/** The current number of chunks in the balloon. */
+	u32 chunks;
+	/** The maximum number of chunks in the balloon. */
+	u32 max_chunks;
+	/**
+	 * Array of pointers to page arrays. A page * array is allocated for
+	 * each chunk when inflating, and freed when the deflating.
+	 */
+	struct page ***pages;
+};
+
+/**
+ * Per bit usage tracker for a u32 mask.
+ *
+ * Used for optimal handling of guest properties and event filter.
+ */
+struct vbg_bit_usage_tracker {
+	/** Per bit usage counters. */
+	u32 per_bit_usage[32];
+	/** The current mask according to per_bit_usage. */
+	u32 mask;
+};
+
+/** VBox guest device (data) extension. */
+struct vbg_dev {
+	struct device *dev;
+	/** The base of the adapter I/O ports. */
+	u16 io_port;
+	/** Pointer to the mapping of the VMMDev adapter memory. */
+	struct vmmdev_memory *mmio;
+	/** Host version */
+	char host_version[64];
+	/** Host features */
+	unsigned int host_features;
+	/**
+	 * Dummy page and vmap address for reserved kernel virtual-address
+	 * space for the guest mappings, only used on hosts lacking vtx.
+	 */
+	struct page *guest_mappings_dummy_page;
+	void *guest_mappings;
+	/** Spinlock protecting pending_events. */
+	spinlock_t event_spinlock;
+	/** Preallocated struct vmmdev_events for the IRQ handler. */
+	struct vmmdev_events *ack_events_req;
+	/** Wait-for-event list for threads waiting for multiple events. */
+	wait_queue_head_t event_wq;
+	/** Mask of pending events. */
+	u32 pending_events;
+	/** Wait-for-event list for threads waiting on HGCM async completion. */
+	wait_queue_head_t hgcm_wq;
+	/** Pre-allocated hgcm cancel2 req. for cancellation on timeout */
+	struct vmmdev_hgcm_cancel2 *cancel_req;
+	/** Mutex protecting cancel_req accesses */
+	struct mutex cancel_req_mutex;
+	/** Pre-allocated mouse-status request for the input-device handling. */
+	struct vmmdev_mouse_status *mouse_status_req;
+	/** Input device for reporting abs mouse coordinates to the guest. */
+	struct input_dev *input;
+
+	/** Memory balloon information. */
+	struct vbg_mem_balloon mem_balloon;
+
+	/** Lock for session related items in vbg_dev and vbg_session */
+	struct mutex session_mutex;
+	/** Events we won't permit anyone to filter out. */
+	u32 fixed_events;
+	/**
+	 * Usage counters for the host events (excludes fixed events),
+	 * Protected by session_mutex.
+	 */
+	struct vbg_bit_usage_tracker event_filter_tracker;
+	/**
+	 * The event filter last reported to the host (or UINT32_MAX).
+	 * Protected by session_mutex.
+	 */
+	u32 event_filter_host;
+
+	/**
+	 * Guest capabilities which have been switched to acquire_mode.
+	 */
+	u32 acquire_mode_guest_caps;
+	/**
+	 * Guest capabilities acquired by vbg_acquire_session_capabilities().
+	 * Only one session can acquire a capability at a time.
+	 */
+	u32 acquired_guest_caps;
+	/**
+	 * Usage counters for guest capabilities requested through
+	 * vbg_set_session_capabilities(). Indexed by capability bit
+	 * number, one count per session using a capability.
+	 * Protected by session_mutex.
+	 */
+	struct vbg_bit_usage_tracker set_guest_caps_tracker;
+	/**
+	 * The guest capabilities last reported to the host (or UINT32_MAX).
+	 * Protected by session_mutex.
+	 */
+	u32 guest_caps_host;
+
+	/**
+	 * Heartbeat timer which fires with interval
+	 * cNsHearbeatInterval and its handler sends
+	 * VMMDEVREQ_GUEST_HEARTBEAT to VMMDev.
+	 */
+	struct timer_list heartbeat_timer;
+	/** Heartbeat timer interval in ms. */
+	int heartbeat_interval_ms;
+	/** Preallocated VMMDEVREQ_GUEST_HEARTBEAT request. */
+	struct vmmdev_request_header *guest_heartbeat_req;
+
+	/** "vboxguest" char-device */
+	struct miscdevice misc_device;
+	/** "vboxuser" char-device */
+	struct miscdevice misc_device_user;
+};
+
+/** The VBoxGuest per session data. */
+struct vbg_session {
+	/** Pointer to the device extension. */
+	struct vbg_dev *gdev;
+
+	/**
+	 * Array containing HGCM client IDs associated with this session.
+	 * These will be automatically disconnected when the session is closed.
+	 * Protected by vbg_gdev.session_mutex.
+	 */
+	u32 hgcm_client_ids[64];
+	/**
+	 * Host events requested by the session.
+	 * An event type requested in any guest session will be added to the
+	 * host filter. Protected by vbg_gdev.session_mutex.
+	 */
+	u32 event_filter;
+	/**
+	 * Guest capabilities acquired by vbg_acquire_session_capabilities().
+	 * Only one session can acquire a capability at a time.
+	 */
+	u32 acquired_guest_caps;
+	/**
+	 * Guest capabilities set through vbg_set_session_capabilities().
+	 * A capability claimed by any guest session will be reported to the
+	 * host. Protected by vbg_gdev.session_mutex.
+	 */
+	u32 set_guest_caps;
+	/** VMMDEV_REQUESTOR_* flags */
+	u32 requestor;
+	/** Set on CANCEL_ALL_WAITEVENTS, protected by vbg_devevent_spinlock. */
+	bool cancel_waiters;
+};
+
+int  vbg_core_init(struct vbg_dev *gdev, u32 fixed_events);
+void vbg_core_exit(struct vbg_dev *gdev);
+struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor);
+void vbg_core_close_session(struct vbg_session *session);
+int  vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data);
+int  vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features);
+
+irqreturn_t vbg_core_isr(int irq, void *dev_id);
+
+void vbg_linux_mouse_event(struct vbg_dev *gdev);
+
+/* Private (non exported) functions form vboxguest_utils.c */
+void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type,
+		    u32 requestor);
+void vbg_req_free(void *req, size_t len);
+int vbg_req_perform(struct vbg_dev *gdev, void *req);
+int vbg_hgcm_call32(
+	struct vbg_dev *gdev, u32 requestor, u32 client_id, u32 function,
+	u32 timeout_ms, struct vmmdev_hgcm_function_parameter32 *parm32,
+	u32 parm_count, int *vbox_status);
+
+#endif

linux-7.2.3/drivers/virt/vboxguest/vboxguest_linux.c

@@ -0,0 +1,502 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * vboxguest linux pci driver, char-dev and input-device code,
+ *
+ * Copyright (C) 2006-2016 Oracle Corporation
+ */
+
+#include <linux/cred.h>
+#include <linux/input.h>
+#include <linux/kernel.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/poll.h>
+#include <linux/vbox_utils.h>
+#include "vboxguest_core.h"
+
+/** The device name. */
+#define DEVICE_NAME		"vboxguest"
+/** The device name for the device node open to everyone. */
+#define DEVICE_NAME_USER	"vboxuser"
+/** VirtualBox PCI vendor ID. */
+#define VBOX_VENDORID		0x80ee
+/** VMMDev PCI card product ID. */
+#define VMMDEV_DEVICEID		0xcafe
+
+/** Mutex protecting the global vbg_gdev pointer used by vbg_get/put_gdev. */
+static DEFINE_MUTEX(vbg_gdev_mutex);
+/** Global vbg_gdev pointer used by vbg_get/put_gdev. */
+static struct vbg_dev *vbg_gdev;
+
+static u32 vbg_misc_device_requestor(struct inode *inode)
+{
+	u32 requestor = VMMDEV_REQUESTOR_USERMODE |
+			VMMDEV_REQUESTOR_CON_DONT_KNOW |
+			VMMDEV_REQUESTOR_TRUST_NOT_GIVEN;
+
+	if (from_kuid(current_user_ns(), current_uid()) == 0)
+		requestor |= VMMDEV_REQUESTOR_USR_ROOT;
+	else
+		requestor |= VMMDEV_REQUESTOR_USR_USER;
+
+	if (in_egroup_p(inode->i_gid))
+		requestor |= VMMDEV_REQUESTOR_GRP_VBOX;
+
+	return requestor;
+}
+
+static int vbg_misc_device_open(struct inode *inode, struct file *filp)
+{
+	struct vbg_session *session;
+	struct vbg_dev *gdev;
+
+	/* misc_open sets filp->private_data to our misc device */
+	gdev = container_of(filp->private_data, struct vbg_dev, misc_device);
+
+	session = vbg_core_open_session(gdev, vbg_misc_device_requestor(inode));
+	if (IS_ERR(session))
+		return PTR_ERR(session);
+
+	filp->private_data = session;
+	return 0;
+}
+
+static int vbg_misc_device_user_open(struct inode *inode, struct file *filp)
+{
+	struct vbg_session *session;
+	struct vbg_dev *gdev;
+
+	/* misc_open sets filp->private_data to our misc device */
+	gdev = container_of(filp->private_data, struct vbg_dev,
+			    misc_device_user);
+
+	session = vbg_core_open_session(gdev, vbg_misc_device_requestor(inode) |
+					      VMMDEV_REQUESTOR_USER_DEVICE);
+	if (IS_ERR(session))
+		return PTR_ERR(session);
+
+	filp->private_data = session;
+	return 0;
+}
+
+/**
+ * vbg_misc_device_close - Close device.
+ * @inode:		Pointer to inode info structure.
+ * @filp:		Associated file pointer.
+ *
+ * Return: %0 on success, negated errno on failure.
+ */
+static int vbg_misc_device_close(struct inode *inode, struct file *filp)
+{
+	vbg_core_close_session(filp->private_data);
+	filp->private_data = NULL;
+	return 0;
+}
+
+/**
+ * vbg_misc_device_ioctl - Device I/O Control entry point.
+ * @filp:		Associated file pointer.
+ * @req:		The request specified to ioctl().
+ * @arg:		The argument specified to ioctl().
+ *
+ * Return: %0 on success, negated errno on failure.
+ */
+static long vbg_misc_device_ioctl(struct file *filp, unsigned int req,
+				  unsigned long arg)
+{
+	struct vbg_session *session = filp->private_data;
+	size_t returned_size, size;
+	struct vbg_ioctl_hdr hdr;
+	bool is_vmmdev_req;
+	int ret = 0;
+	void *buf;
+
+	if (copy_from_user(&hdr, (void *)arg, sizeof(hdr)))
+		return -EFAULT;
+
+	if (hdr.version != VBG_IOCTL_HDR_VERSION)
+		return -EINVAL;
+
+	if (hdr.size_in < sizeof(hdr) ||
+	    (hdr.size_out && hdr.size_out < sizeof(hdr)))
+		return -EINVAL;
+
+	size = max(hdr.size_in, hdr.size_out);
+	if (_IOC_SIZE(req) && _IOC_SIZE(req) != size)
+		return -EINVAL;
+	if (size > SZ_16M)
+		return -E2BIG;
+
+	/*
+	 * IOCTL_VMMDEV_REQUEST needs the buffer to be below 4G to avoid
+	 * the need for a bounce-buffer and another copy later on.
+	 */
+	is_vmmdev_req = (req & ~IOCSIZE_MASK) == VBG_IOCTL_VMMDEV_REQUEST(0) ||
+			 req == VBG_IOCTL_VMMDEV_REQUEST_BIG ||
+			 req == VBG_IOCTL_VMMDEV_REQUEST_BIG_ALT;
+
+	if (is_vmmdev_req)
+		buf = vbg_req_alloc(size, VBG_IOCTL_HDR_TYPE_DEFAULT,
+				    session->requestor);
+	else
+		buf = kmalloc(size, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	*((struct vbg_ioctl_hdr *)buf) = hdr;
+	if (copy_from_user(buf + sizeof(hdr), (void *)arg + sizeof(hdr),
+			   hdr.size_in - sizeof(hdr))) {
+		ret = -EFAULT;
+		goto out;
+	}
+	if (hdr.size_in < size)
+		memset(buf + hdr.size_in, 0, size -  hdr.size_in);
+
+	ret = vbg_core_ioctl(session, req, buf);
+	if (ret)
+		goto out;
+
+	returned_size = ((struct vbg_ioctl_hdr *)buf)->size_out;
+	if (returned_size > size) {
+		vbg_debug("%s: too much output data %zu > %zu\n",
+			  __func__, returned_size, size);
+		returned_size = size;
+	}
+	if (copy_to_user((void *)arg, buf, returned_size) != 0)
+		ret = -EFAULT;
+
+out:
+	if (is_vmmdev_req)
+		vbg_req_free(buf, size);
+	else
+		kfree(buf);
+
+	return ret;
+}
+
+/* The file_operations structures. */
+static const struct file_operations vbg_misc_device_fops = {
+	.owner			= THIS_MODULE,
+	.open			= vbg_misc_device_open,
+	.release		= vbg_misc_device_close,
+	.unlocked_ioctl		= vbg_misc_device_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= vbg_misc_device_ioctl,
+#endif
+};
+static const struct file_operations vbg_misc_device_user_fops = {
+	.owner			= THIS_MODULE,
+	.open			= vbg_misc_device_user_open,
+	.release		= vbg_misc_device_close,
+	.unlocked_ioctl		= vbg_misc_device_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl		= vbg_misc_device_ioctl,
+#endif
+};
+
+/*
+ * Called when the input device is first opened.
+ *
+ * Sets up absolute mouse reporting.
+ */
+static int vbg_input_open(struct input_dev *input)
+{
+	struct vbg_dev *gdev = input_get_drvdata(input);
+	u32 feat = VMMDEV_MOUSE_GUEST_CAN_ABSOLUTE | VMMDEV_MOUSE_NEW_PROTOCOL;
+
+	return vbg_core_set_mouse_status(gdev, feat);
+}
+
+/*
+ * Called if all open handles to the input device are closed.
+ *
+ * Disables absolute reporting.
+ */
+static void vbg_input_close(struct input_dev *input)
+{
+	struct vbg_dev *gdev = input_get_drvdata(input);
+
+	vbg_core_set_mouse_status(gdev, 0);
+}
+
+/*
+ * Creates the kernel input device.
+ *
+ * Return: 0 on success, negated errno on failure.
+ */
+static int vbg_create_input_device(struct vbg_dev *gdev)
+{
+	struct input_dev *input;
+
+	input = devm_input_allocate_device(gdev->dev);
+	if (!input)
+		return -ENOMEM;
+
+	input->id.bustype = BUS_PCI;
+	input->id.vendor = VBOX_VENDORID;
+	input->id.product = VMMDEV_DEVICEID;
+	input->open = vbg_input_open;
+	input->close = vbg_input_close;
+	input->dev.parent = gdev->dev;
+	input->name = "VirtualBox mouse integration";
+
+	input_set_abs_params(input, ABS_X, VMMDEV_MOUSE_RANGE_MIN,
+			     VMMDEV_MOUSE_RANGE_MAX, 0, 0);
+	input_set_abs_params(input, ABS_Y, VMMDEV_MOUSE_RANGE_MIN,
+			     VMMDEV_MOUSE_RANGE_MAX, 0, 0);
+	input_set_capability(input, EV_KEY, BTN_MOUSE);
+	input_set_drvdata(input, gdev);
+
+	gdev->input = input;
+
+	return input_register_device(gdev->input);
+}
+
+static ssize_t host_version_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct vbg_dev *gdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", gdev->host_version);
+}
+
+static ssize_t host_features_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct vbg_dev *gdev = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%#x\n", gdev->host_features);
+}
+
+static DEVICE_ATTR_RO(host_version);
+static DEVICE_ATTR_RO(host_features);
+
+static struct attribute *vbg_pci_attrs[] = {
+	&dev_attr_host_version.attr,
+	&dev_attr_host_features.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(vbg_pci);
+
+/*
+ * Does the PCI detection and init of the device.
+ *
+ * Return: 0 on success, negated errno on failure.
+ */
+static int vbg_pci_probe(struct pci_dev *pci, const struct pci_device_id *id)
+{
+	struct device *dev = &pci->dev;
+	resource_size_t io, io_len, mmio, mmio_len;
+	struct vmmdev_memory *vmmdev;
+	struct vbg_dev *gdev;
+	int ret;
+
+	gdev = devm_kzalloc(dev, sizeof(*gdev), GFP_KERNEL);
+	if (!gdev)
+		return -ENOMEM;
+
+	ret = pci_enable_device(pci);
+	if (ret != 0) {
+		vbg_err("vboxguest: Error enabling device: %d\n", ret);
+		return ret;
+	}
+
+	ret = -ENODEV;
+
+	io = pci_resource_start(pci, 0);
+	io_len = pci_resource_len(pci, 0);
+	if (!io || !io_len) {
+		vbg_err("vboxguest: Error IO-port resource (0) is missing\n");
+		goto err_disable_pcidev;
+	}
+	if (devm_request_region(dev, io, io_len, DEVICE_NAME) == NULL) {
+		vbg_err("vboxguest: Error could not claim IO resource\n");
+		ret = -EBUSY;
+		goto err_disable_pcidev;
+	}
+
+	mmio = pci_resource_start(pci, 1);
+	mmio_len = pci_resource_len(pci, 1);
+	if (!mmio || !mmio_len) {
+		vbg_err("vboxguest: Error MMIO resource (1) is missing\n");
+		goto err_disable_pcidev;
+	}
+
+	if (devm_request_mem_region(dev, mmio, mmio_len, DEVICE_NAME) == NULL) {
+		vbg_err("vboxguest: Error could not claim MMIO resource\n");
+		ret = -EBUSY;
+		goto err_disable_pcidev;
+	}
+
+	vmmdev = devm_ioremap(dev, mmio, mmio_len);
+	if (!vmmdev) {
+		vbg_err("vboxguest: Error ioremap failed; MMIO addr=%pap size=%pap\n",
+			&mmio, &mmio_len);
+		goto err_disable_pcidev;
+	}
+
+	/* Validate MMIO region version and size. */
+	if (vmmdev->version != VMMDEV_MEMORY_VERSION ||
+	    vmmdev->size < 32 || vmmdev->size > mmio_len) {
+		vbg_err("vboxguest: Bogus VMMDev memory; version=%08x (expected %08x) size=%d (expected <= %d)\n",
+			vmmdev->version, VMMDEV_MEMORY_VERSION,
+			vmmdev->size, (int)mmio_len);
+		goto err_disable_pcidev;
+	}
+
+	gdev->io_port = io;
+	gdev->mmio = vmmdev;
+	gdev->dev = dev;
+	gdev->misc_device.minor = MISC_DYNAMIC_MINOR;
+	gdev->misc_device.name = DEVICE_NAME;
+	gdev->misc_device.fops = &vbg_misc_device_fops;
+	gdev->misc_device_user.minor = MISC_DYNAMIC_MINOR;
+	gdev->misc_device_user.name = DEVICE_NAME_USER;
+	gdev->misc_device_user.fops = &vbg_misc_device_user_fops;
+
+	ret = vbg_core_init(gdev, VMMDEV_EVENT_MOUSE_POSITION_CHANGED);
+	if (ret)
+		goto err_disable_pcidev;
+
+	ret = vbg_create_input_device(gdev);
+	if (ret) {
+		vbg_err("vboxguest: Error creating input device: %d\n", ret);
+		goto err_vbg_core_exit;
+	}
+
+	ret = request_irq(pci->irq, vbg_core_isr, IRQF_SHARED, DEVICE_NAME,
+			  gdev);
+	if (ret) {
+		vbg_err("vboxguest: Error requesting irq: %d\n", ret);
+		goto err_vbg_core_exit;
+	}
+
+	ret = misc_register(&gdev->misc_device);
+	if (ret) {
+		vbg_err("vboxguest: Error misc_register %s failed: %d\n",
+			DEVICE_NAME, ret);
+		goto err_free_irq;
+	}
+
+	ret = misc_register(&gdev->misc_device_user);
+	if (ret) {
+		vbg_err("vboxguest: Error misc_register %s failed: %d\n",
+			DEVICE_NAME_USER, ret);
+		goto err_unregister_misc_device;
+	}
+
+	mutex_lock(&vbg_gdev_mutex);
+	if (!vbg_gdev)
+		vbg_gdev = gdev;
+	else
+		ret = -EBUSY;
+	mutex_unlock(&vbg_gdev_mutex);
+
+	if (ret) {
+		vbg_err("vboxguest: Error more then 1 vbox guest pci device\n");
+		goto err_unregister_misc_device_user;
+	}
+
+	pci_set_drvdata(pci, gdev);
+
+	return 0;
+
+err_unregister_misc_device_user:
+	misc_deregister(&gdev->misc_device_user);
+err_unregister_misc_device:
+	misc_deregister(&gdev->misc_device);
+err_free_irq:
+	free_irq(pci->irq, gdev);
+err_vbg_core_exit:
+	vbg_core_exit(gdev);
+err_disable_pcidev:
+	pci_disable_device(pci);
+
+	return ret;
+}
+
+static void vbg_pci_remove(struct pci_dev *pci)
+{
+	struct vbg_dev *gdev = pci_get_drvdata(pci);
+
+	mutex_lock(&vbg_gdev_mutex);
+	vbg_gdev = NULL;
+	mutex_unlock(&vbg_gdev_mutex);
+
+	free_irq(pci->irq, gdev);
+	misc_deregister(&gdev->misc_device_user);
+	misc_deregister(&gdev->misc_device);
+	vbg_core_exit(gdev);
+	pci_disable_device(pci);
+}
+
+struct vbg_dev *vbg_get_gdev(void)
+{
+	mutex_lock(&vbg_gdev_mutex);
+
+	/*
+	 * Note on success we keep the mutex locked until vbg_put_gdev(),
+	 * this stops vbg_pci_remove from removing the device from underneath
+	 * vboxsf. vboxsf will only hold a reference for a short while.
+	 */
+	if (vbg_gdev)
+		return vbg_gdev;
+
+	mutex_unlock(&vbg_gdev_mutex);
+	return ERR_PTR(-ENODEV);
+}
+EXPORT_SYMBOL(vbg_get_gdev);
+
+void vbg_put_gdev(struct vbg_dev *gdev)
+{
+	WARN_ON(gdev != vbg_gdev);
+	mutex_unlock(&vbg_gdev_mutex);
+}
+EXPORT_SYMBOL(vbg_put_gdev);
+
+/*
+ * Callback for mouse events.
+ *
+ * This is called at the end of the ISR, after leaving the event spinlock, if
+ * VMMDEV_EVENT_MOUSE_POSITION_CHANGED was raised by the host.
+ *
+ * @gdev:		The device extension.
+ */
+void vbg_linux_mouse_event(struct vbg_dev *gdev)
+{
+	int rc;
+
+	/* Report events to the kernel input device */
+	gdev->mouse_status_req->mouse_features = 0;
+	gdev->mouse_status_req->pointer_pos_x = 0;
+	gdev->mouse_status_req->pointer_pos_y = 0;
+	rc = vbg_req_perform(gdev, gdev->mouse_status_req);
+	if (rc >= 0) {
+		input_report_abs(gdev->input, ABS_X,
+				 gdev->mouse_status_req->pointer_pos_x);
+		input_report_abs(gdev->input, ABS_Y,
+				 gdev->mouse_status_req->pointer_pos_y);
+		input_sync(gdev->input);
+	}
+}
+
+static const struct pci_device_id vbg_pci_ids[] = {
+	{ .vendor = VBOX_VENDORID, .device = VMMDEV_DEVICEID },
+	{}
+};
+MODULE_DEVICE_TABLE(pci,  vbg_pci_ids);
+
+static struct pci_driver vbg_pci_driver = {
+	.name		= DEVICE_NAME,
+	.dev_groups	= vbg_pci_groups,
+	.id_table	= vbg_pci_ids,
+	.probe		= vbg_pci_probe,
+	.remove		= vbg_pci_remove,
+};
+
+module_pci_driver(vbg_pci_driver);
+
+MODULE_AUTHOR("Oracle Corporation");
+MODULE_DESCRIPTION("Oracle VM VirtualBox Guest Additions for Linux Module");
+MODULE_LICENSE("GPL");

linux-7.2.3/drivers/virt/vboxguest/vboxguest_utils.c

@@ -0,0 +1,834 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */
+/*
+ * vboxguest vmm-req and hgcm-call code, VBoxGuestR0LibHGCMInternal.cpp,
+ * VBoxGuestR0LibGenericRequest.cpp and RTErrConvertToErrno.cpp in vbox svn.
+ *
+ * Copyright (C) 2006-2016 Oracle Corporation
+ */
+
+#include <linux/errno.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/vbox_err.h>
+#include <linux/vbox_utils.h>
+#include "vboxguest_core.h"
+
+/* Get the pointer to the first parameter of a HGCM call request. */
+#define VMMDEV_HGCM_CALL_PARMS(a) \
+	((struct vmmdev_hgcm_function_parameter *)( \
+		(u8 *)(a) + sizeof(struct vmmdev_hgcm_call)))
+
+/* The max parameter buffer size for a user request. */
+#define VBG_MAX_HGCM_USER_PARM		(24 * SZ_1M)
+/* The max parameter buffer size for a kernel request. */
+#define VBG_MAX_HGCM_KERNEL_PARM	(16 * SZ_1M)
+
+#define VBG_DEBUG_PORT			0x504
+
+/* This protects vbg_log_buf and serializes VBG_DEBUG_PORT accesses */
+static DEFINE_SPINLOCK(vbg_log_lock);
+static char vbg_log_buf[128];
+
+#define VBG_LOG(name, pr_func) \
+void name(const char *fmt, ...)						\
+{									\
+	unsigned long flags;						\
+	va_list args;							\
+	int i, count;							\
+									\
+	va_start(args, fmt);						\
+	spin_lock_irqsave(&vbg_log_lock, flags);			\
+									\
+	count = vscnprintf(vbg_log_buf, sizeof(vbg_log_buf), fmt, args);\
+	for (i = 0; i < count; i++)					\
+		outb(vbg_log_buf[i], VBG_DEBUG_PORT);			\
+									\
+	pr_func("%s", vbg_log_buf);					\
+									\
+	spin_unlock_irqrestore(&vbg_log_lock, flags);			\
+	va_end(args);							\
+}									\
+EXPORT_SYMBOL(name)
+
+VBG_LOG(vbg_info, pr_info);
+VBG_LOG(vbg_warn, pr_warn);
+VBG_LOG(vbg_err, pr_err);
+VBG_LOG(vbg_err_ratelimited, pr_err_ratelimited);
+#if defined(DEBUG) && !defined(CONFIG_DYNAMIC_DEBUG)
+VBG_LOG(vbg_debug, pr_debug);
+#endif
+
+void *vbg_req_alloc(size_t len, enum vmmdev_request_type req_type,
+		    u32 requestor)
+{
+	struct vmmdev_request_header *req;
+	int order = get_order(PAGE_ALIGN(len));
+
+	req = (void *)__get_free_pages(GFP_KERNEL | GFP_DMA32, order);
+	if (!req)
+		return NULL;
+
+	memset(req, 0xaa, len);
+
+	req->size = len;
+	req->version = VMMDEV_REQUEST_HEADER_VERSION;
+	req->request_type = req_type;
+	req->rc = VERR_GENERAL_FAILURE;
+	req->reserved1 = 0;
+	req->requestor = requestor;
+
+	return req;
+}
+
+void vbg_req_free(void *req, size_t len)
+{
+	if (!req)
+		return;
+
+	free_pages((unsigned long)req, get_order(PAGE_ALIGN(len)));
+}
+
+/* Note this function returns a VBox status code, not a negative errno!! */
+int vbg_req_perform(struct vbg_dev *gdev, void *req)
+{
+	unsigned long phys_req = virt_to_phys(req);
+
+	outl(phys_req, gdev->io_port + VMMDEV_PORT_OFF_REQUEST);
+	/*
+	 * The host changes the request as a result of the outl, make sure
+	 * the outl and any reads of the req happen in the correct order.
+	 */
+	mb();
+
+	return ((struct vmmdev_request_header *)req)->rc;
+}
+
+static bool hgcm_req_done(struct vbg_dev *gdev,
+			  struct vmmdev_hgcmreq_header *header)
+{
+	unsigned long flags;
+	bool done;
+
+	spin_lock_irqsave(&gdev->event_spinlock, flags);
+	done = header->flags & VMMDEV_HGCM_REQ_DONE;
+	spin_unlock_irqrestore(&gdev->event_spinlock, flags);
+
+	return done;
+}
+
+int vbg_hgcm_connect(struct vbg_dev *gdev, u32 requestor,
+		     struct vmmdev_hgcm_service_location *loc,
+		     u32 *client_id, int *vbox_status)
+{
+	struct vmmdev_hgcm_connect *hgcm_connect = NULL;
+	int rc;
+
+	hgcm_connect = vbg_req_alloc(sizeof(*hgcm_connect),
+				     VMMDEVREQ_HGCM_CONNECT, requestor);
+	if (!hgcm_connect)
+		return -ENOMEM;
+
+	hgcm_connect->header.flags = 0;
+	memcpy(&hgcm_connect->loc, loc, sizeof(*loc));
+	hgcm_connect->client_id = 0;
+
+	rc = vbg_req_perform(gdev, hgcm_connect);
+
+	if (rc == VINF_HGCM_ASYNC_EXECUTE)
+		wait_event(gdev->hgcm_wq,
+			   hgcm_req_done(gdev, &hgcm_connect->header));
+
+	if (rc >= 0) {
+		*client_id = hgcm_connect->client_id;
+		rc = hgcm_connect->header.result;
+	}
+
+	vbg_req_free(hgcm_connect, sizeof(*hgcm_connect));
+
+	*vbox_status = rc;
+	return 0;
+}
+EXPORT_SYMBOL(vbg_hgcm_connect);
+
+int vbg_hgcm_disconnect(struct vbg_dev *gdev, u32 requestor,
+			u32 client_id, int *vbox_status)
+{
+	struct vmmdev_hgcm_disconnect *hgcm_disconnect = NULL;
+	int rc;
+
+	hgcm_disconnect = vbg_req_alloc(sizeof(*hgcm_disconnect),
+					VMMDEVREQ_HGCM_DISCONNECT,
+					requestor);
+	if (!hgcm_disconnect)
+		return -ENOMEM;
+
+	hgcm_disconnect->header.flags = 0;
+	hgcm_disconnect->client_id = client_id;
+
+	rc = vbg_req_perform(gdev, hgcm_disconnect);
+
+	if (rc == VINF_HGCM_ASYNC_EXECUTE)
+		wait_event(gdev->hgcm_wq,
+			   hgcm_req_done(gdev, &hgcm_disconnect->header));
+
+	if (rc >= 0)
+		rc = hgcm_disconnect->header.result;
+
+	vbg_req_free(hgcm_disconnect, sizeof(*hgcm_disconnect));
+
+	*vbox_status = rc;
+	return 0;
+}
+EXPORT_SYMBOL(vbg_hgcm_disconnect);
+
+static u32 hgcm_call_buf_size_in_pages(void *buf, u32 len)
+{
+	u32 size = PAGE_ALIGN(len + ((unsigned long)buf & ~PAGE_MASK));
+
+	return size >> PAGE_SHIFT;
+}
+
+static void hgcm_call_add_pagelist_size(void *buf, u32 len, size_t *extra)
+{
+	u32 page_count;
+
+	page_count = hgcm_call_buf_size_in_pages(buf, len);
+	*extra += offsetof(struct vmmdev_hgcm_pagelist, pages[page_count]);
+}
+
+static int hgcm_call_preprocess_linaddr(
+	const struct vmmdev_hgcm_function_parameter *src_parm,
+	void **bounce_buf_ret, size_t *extra)
+{
+	void *buf, *bounce_buf;
+	bool copy_in;
+	u32 len;
+	int ret;
+
+	buf = (void *)src_parm->u.pointer.u.linear_addr;
+	len = src_parm->u.pointer.size;
+	copy_in = src_parm->type != VMMDEV_HGCM_PARM_TYPE_LINADDR_OUT;
+
+	if (len > VBG_MAX_HGCM_USER_PARM)
+		return -E2BIG;
+
+	bounce_buf = kvmalloc(len, GFP_KERNEL);
+	if (!bounce_buf)
+		return -ENOMEM;
+
+	*bounce_buf_ret = bounce_buf;
+
+	if (copy_in) {
+		ret = copy_from_user(bounce_buf, (void __user *)buf, len);
+		if (ret)
+			return -EFAULT;
+	} else {
+		memset(bounce_buf, 0, len);
+	}
+
+	hgcm_call_add_pagelist_size(bounce_buf, len, extra);
+	return 0;
+}
+
+/**
+ * hgcm_call_preprocess - Preprocesses the HGCM call, validate parameters,
+ *	alloc bounce buffers and figure out how much extra storage we need for
+ *	page lists.
+ * @src_parm:         Pointer to source function call parameters
+ * @parm_count:       Number of function call parameters.
+ * @bounce_bufs_ret:  Where to return the allocated bouncebuffer array
+ * @extra:            Where to return the extra request space needed for
+ *                    physical page lists.
+ *
+ * Return: %0 or negative errno value.
+ */
+static int hgcm_call_preprocess(
+	const struct vmmdev_hgcm_function_parameter *src_parm,
+	u32 parm_count, void ***bounce_bufs_ret, size_t *extra)
+{
+	void *buf, **bounce_bufs = NULL;
+	u32 i, len;
+	int ret;
+
+	for (i = 0; i < parm_count; i++, src_parm++) {
+		switch (src_parm->type) {
+		case VMMDEV_HGCM_PARM_TYPE_32BIT:
+		case VMMDEV_HGCM_PARM_TYPE_64BIT:
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_IN:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_OUT:
+			if (!bounce_bufs) {
+				bounce_bufs = kcalloc(parm_count,
+						      sizeof(void *),
+						      GFP_KERNEL);
+				if (!bounce_bufs)
+					return -ENOMEM;
+
+				*bounce_bufs_ret = bounce_bufs;
+			}
+
+			ret = hgcm_call_preprocess_linaddr(src_parm,
+							   &bounce_bufs[i],
+							   extra);
+			if (ret)
+				return ret;
+
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT:
+			buf = (void *)src_parm->u.pointer.u.linear_addr;
+			len = src_parm->u.pointer.size;
+			if (WARN_ON(len > VBG_MAX_HGCM_KERNEL_PARM))
+				return -E2BIG;
+
+			hgcm_call_add_pagelist_size(buf, len, extra);
+			break;
+
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * hgcm_call_linear_addr_type_to_pagelist_flags - Translates linear address
+ *	types to page list direction flags.
+ * @type:  The type.
+ *
+ * Return: page list flags.
+ */
+static u32 hgcm_call_linear_addr_type_to_pagelist_flags(
+	enum vmmdev_hgcm_function_parameter_type type)
+{
+	switch (type) {
+	default:
+		WARN_ON(1);
+		fallthrough;
+	case VMMDEV_HGCM_PARM_TYPE_LINADDR:
+	case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL:
+		return VMMDEV_HGCM_F_PARM_DIRECTION_BOTH;
+
+	case VMMDEV_HGCM_PARM_TYPE_LINADDR_IN:
+	case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN:
+		return VMMDEV_HGCM_F_PARM_DIRECTION_TO_HOST;
+
+	case VMMDEV_HGCM_PARM_TYPE_LINADDR_OUT:
+	case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT:
+		return VMMDEV_HGCM_F_PARM_DIRECTION_FROM_HOST;
+	}
+}
+
+static void hgcm_call_init_linaddr(struct vmmdev_hgcm_call *call,
+	struct vmmdev_hgcm_function_parameter *dst_parm, void *buf, u32 len,
+	enum vmmdev_hgcm_function_parameter_type type, u32 *off_extra)
+{
+	struct vmmdev_hgcm_pagelist *dst_pg_lst;
+	struct page *page;
+	bool is_vmalloc;
+	u32 i, page_count;
+
+	dst_parm->type = type;
+
+	if (len == 0) {
+		dst_parm->u.pointer.size = 0;
+		dst_parm->u.pointer.u.linear_addr = 0;
+		return;
+	}
+
+	dst_pg_lst = (void *)call + *off_extra;
+	page_count = hgcm_call_buf_size_in_pages(buf, len);
+	is_vmalloc = is_vmalloc_addr(buf);
+
+	dst_parm->type = VMMDEV_HGCM_PARM_TYPE_PAGELIST;
+	dst_parm->u.page_list.size = len;
+	dst_parm->u.page_list.offset = *off_extra;
+	dst_pg_lst->flags = hgcm_call_linear_addr_type_to_pagelist_flags(type);
+	dst_pg_lst->offset_first_page = (unsigned long)buf & ~PAGE_MASK;
+	dst_pg_lst->page_count = page_count;
+
+	for (i = 0; i < page_count; i++) {
+		if (is_vmalloc)
+			page = vmalloc_to_page(buf);
+		else
+			page = virt_to_page(buf);
+
+		dst_pg_lst->pages[i] = page_to_phys(page);
+		buf += PAGE_SIZE;
+	}
+
+	*off_extra += offsetof(struct vmmdev_hgcm_pagelist, pages[page_count]);
+}
+
+/**
+ * hgcm_call_init_call - Initializes the call request that we're sending
+ *	to the host.
+ * @call:            The call to initialize.
+ * @client_id:       The client ID of the caller.
+ * @function:        The function number of the function to call.
+ * @src_parm:        Pointer to source function call parameters.
+ * @parm_count:      Number of function call parameters.
+ * @bounce_bufs:     The bouncebuffer array.
+ */
+static void hgcm_call_init_call(
+	struct vmmdev_hgcm_call *call, u32 client_id, u32 function,
+	const struct vmmdev_hgcm_function_parameter *src_parm,
+	u32 parm_count, void **bounce_bufs)
+{
+	struct vmmdev_hgcm_function_parameter *dst_parm =
+		VMMDEV_HGCM_CALL_PARMS(call);
+	u32 i, off_extra = (uintptr_t)(dst_parm + parm_count) - (uintptr_t)call;
+	void *buf;
+
+	call->header.flags = 0;
+	call->header.result = VINF_SUCCESS;
+	call->client_id = client_id;
+	call->function = function;
+	call->parm_count = parm_count;
+
+	for (i = 0; i < parm_count; i++, src_parm++, dst_parm++) {
+		switch (src_parm->type) {
+		case VMMDEV_HGCM_PARM_TYPE_32BIT:
+		case VMMDEV_HGCM_PARM_TYPE_64BIT:
+			*dst_parm = *src_parm;
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_IN:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_OUT:
+			hgcm_call_init_linaddr(call, dst_parm, bounce_bufs[i],
+					       src_parm->u.pointer.size,
+					       src_parm->type, &off_extra);
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT:
+			buf = (void *)src_parm->u.pointer.u.linear_addr;
+			hgcm_call_init_linaddr(call, dst_parm, buf,
+					       src_parm->u.pointer.size,
+					       src_parm->type, &off_extra);
+			break;
+
+		default:
+			WARN_ON(1);
+			dst_parm->type = VMMDEV_HGCM_PARM_TYPE_INVALID;
+		}
+	}
+}
+
+/**
+ * hgcm_cancel_call - Tries to cancel a pending HGCM call.
+ * @gdev:        The VBoxGuest device extension.
+ * @call:        The call to cancel.
+ *
+ * Return: VBox status code
+ */
+static int hgcm_cancel_call(struct vbg_dev *gdev, struct vmmdev_hgcm_call *call)
+{
+	int rc;
+
+	/*
+	 * We use a pre-allocated request for cancellations, which is
+	 * protected by cancel_req_mutex. This means that all cancellations
+	 * get serialized, this should be fine since they should be rare.
+	 */
+	mutex_lock(&gdev->cancel_req_mutex);
+	gdev->cancel_req->phys_req_to_cancel = virt_to_phys(call);
+	rc = vbg_req_perform(gdev, gdev->cancel_req);
+	mutex_unlock(&gdev->cancel_req_mutex);
+
+	if (rc == VERR_NOT_IMPLEMENTED) {
+		call->header.flags |= VMMDEV_HGCM_REQ_CANCELLED;
+		call->header.header.request_type = VMMDEVREQ_HGCM_CANCEL;
+
+		rc = vbg_req_perform(gdev, call);
+		if (rc == VERR_INVALID_PARAMETER)
+			rc = VERR_NOT_FOUND;
+	}
+
+	if (rc >= 0)
+		call->header.flags |= VMMDEV_HGCM_REQ_CANCELLED;
+
+	return rc;
+}
+
+/**
+ * vbg_hgcm_do_call - Performs the call and completion wait.
+ * @gdev:        The VBoxGuest device extension.
+ * @call:        The call to execute.
+ * @timeout_ms:  Timeout in ms.
+ * @interruptible: whether this call is interruptible
+ * @leak_it:     Where to return the leak it / free it, indicator.
+ *               Cancellation fun.
+ *
+ * Return: %0 or negative errno value.
+ */
+static int vbg_hgcm_do_call(struct vbg_dev *gdev, struct vmmdev_hgcm_call *call,
+			    u32 timeout_ms, bool interruptible, bool *leak_it)
+{
+	int rc, cancel_rc, ret;
+	long timeout;
+
+	*leak_it = false;
+
+	rc = vbg_req_perform(gdev, call);
+
+	/*
+	 * If the call failed, then pretend success. Upper layers will
+	 * interpret the result code in the packet.
+	 */
+	if (rc < 0) {
+		call->header.result = rc;
+		return 0;
+	}
+
+	if (rc != VINF_HGCM_ASYNC_EXECUTE)
+		return 0;
+
+	/* Host decided to process the request asynchronously, wait for it */
+	if (timeout_ms == U32_MAX)
+		timeout = MAX_SCHEDULE_TIMEOUT;
+	else
+		timeout = msecs_to_jiffies(timeout_ms);
+
+	if (interruptible) {
+		timeout = wait_event_interruptible_timeout(gdev->hgcm_wq,
+							   hgcm_req_done(gdev, &call->header),
+							   timeout);
+	} else {
+		timeout = wait_event_timeout(gdev->hgcm_wq,
+					     hgcm_req_done(gdev, &call->header),
+					     timeout);
+	}
+
+	/* timeout > 0 means hgcm_req_done has returned true, so success */
+	if (timeout > 0)
+		return 0;
+
+	if (timeout == 0)
+		ret = -ETIMEDOUT;
+	else
+		ret = -EINTR;
+
+	/* Cancel the request */
+	cancel_rc = hgcm_cancel_call(gdev, call);
+	if (cancel_rc >= 0)
+		return ret;
+
+	/*
+	 * Failed to cancel, this should mean that the cancel has lost the
+	 * race with normal completion, wait while the host completes it.
+	 */
+	if (cancel_rc == VERR_NOT_FOUND || cancel_rc == VERR_SEM_DESTROYED)
+		timeout = msecs_to_jiffies(500);
+	else
+		timeout = msecs_to_jiffies(2000);
+
+	timeout = wait_event_timeout(gdev->hgcm_wq,
+				     hgcm_req_done(gdev, &call->header),
+				     timeout);
+
+	if (WARN_ON(timeout == 0)) {
+		/* We really should never get here */
+		vbg_err("%s: Call timedout and cancellation failed, leaking the request\n",
+			__func__);
+		*leak_it = true;
+		return ret;
+	}
+
+	/* The call has completed normally after all */
+	return 0;
+}
+
+/**
+ * hgcm_call_copy_back_result - Copies the result of the call back to
+ *	the caller info structure and user buffers.
+ * @call:            HGCM call request.
+ * @dst_parm:        Pointer to function call parameters destination.
+ * @parm_count:      Number of function call parameters.
+ * @bounce_bufs:     The bouncebuffer array.
+ *
+ * Return: %0 or negative errno value.
+ */
+static int hgcm_call_copy_back_result(
+	const struct vmmdev_hgcm_call *call,
+	struct vmmdev_hgcm_function_parameter *dst_parm,
+	u32 parm_count, void **bounce_bufs)
+{
+	const struct vmmdev_hgcm_function_parameter *src_parm =
+		VMMDEV_HGCM_CALL_PARMS(call);
+	void __user *p;
+	int ret;
+	u32 i;
+
+	/* Copy back parameters. */
+	for (i = 0; i < parm_count; i++, src_parm++, dst_parm++) {
+		switch (dst_parm->type) {
+		case VMMDEV_HGCM_PARM_TYPE_32BIT:
+		case VMMDEV_HGCM_PARM_TYPE_64BIT:
+			*dst_parm = *src_parm;
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_PAGELIST:
+			dst_parm->u.page_list.size = src_parm->u.page_list.size;
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_IN:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_IN:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_KERNEL_OUT:
+			dst_parm->u.pointer.size = src_parm->u.pointer.size;
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_OUT:
+			dst_parm->u.pointer.size = src_parm->u.pointer.size;
+
+			p = (void __user *)dst_parm->u.pointer.u.linear_addr;
+			ret = copy_to_user(p, bounce_bufs[i],
+					   min(src_parm->u.pointer.size,
+					       dst_parm->u.pointer.size));
+			if (ret)
+				return -EFAULT;
+			break;
+
+		default:
+			WARN_ON(1);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+int vbg_hgcm_call(struct vbg_dev *gdev, u32 requestor, u32 client_id,
+		  u32 function, u32 timeout_ms,
+		  struct vmmdev_hgcm_function_parameter *parms, u32 parm_count,
+		  int *vbox_status)
+{
+	struct vmmdev_hgcm_call *call;
+	void **bounce_bufs = NULL;
+	bool leak_it;
+	size_t size;
+	int i, ret;
+
+	size = sizeof(struct vmmdev_hgcm_call) +
+		   parm_count * sizeof(struct vmmdev_hgcm_function_parameter);
+	/*
+	 * Validate and buffer the parameters for the call. This also increases
+	 * call_size with the amount of extra space needed for page lists.
+	 */
+	ret = hgcm_call_preprocess(parms, parm_count, &bounce_bufs, &size);
+	if (ret) {
+		/* Even on error bounce bufs may still have been allocated */
+		goto free_bounce_bufs;
+	}
+
+	call = vbg_req_alloc(size, VMMDEVREQ_HGCM_CALL, requestor);
+	if (!call) {
+		ret = -ENOMEM;
+		goto free_bounce_bufs;
+	}
+
+	hgcm_call_init_call(call, client_id, function, parms, parm_count,
+			    bounce_bufs);
+
+	ret = vbg_hgcm_do_call(gdev, call, timeout_ms,
+			       requestor & VMMDEV_REQUESTOR_USERMODE, &leak_it);
+	if (ret == 0) {
+		*vbox_status = call->header.result;
+		ret = hgcm_call_copy_back_result(call, parms, parm_count,
+						 bounce_bufs);
+	}
+
+	if (!leak_it)
+		vbg_req_free(call, size);
+
+free_bounce_bufs:
+	if (bounce_bufs) {
+		for (i = 0; i < parm_count; i++)
+			kvfree(bounce_bufs[i]);
+		kfree(bounce_bufs);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(vbg_hgcm_call);
+
+#ifdef CONFIG_COMPAT
+int vbg_hgcm_call32(
+	struct vbg_dev *gdev, u32 requestor, u32 client_id, u32 function,
+	u32 timeout_ms, struct vmmdev_hgcm_function_parameter32 *parm32,
+	u32 parm_count, int *vbox_status)
+{
+	struct vmmdev_hgcm_function_parameter *parm64 = NULL;
+	u32 i, size;
+	int ret = 0;
+
+	/* KISS allocate a temporary request and convert the parameters. */
+	size = parm_count * sizeof(struct vmmdev_hgcm_function_parameter);
+	parm64 = kzalloc(size, GFP_KERNEL);
+	if (!parm64)
+		return -ENOMEM;
+
+	for (i = 0; i < parm_count; i++) {
+		switch (parm32[i].type) {
+		case VMMDEV_HGCM_PARM_TYPE_32BIT:
+			parm64[i].type = VMMDEV_HGCM_PARM_TYPE_32BIT;
+			parm64[i].u.value32 = parm32[i].u.value32;
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_64BIT:
+			parm64[i].type = VMMDEV_HGCM_PARM_TYPE_64BIT;
+			parm64[i].u.value64 = parm32[i].u.value64;
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_OUT:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_IN:
+			parm64[i].type = parm32[i].type;
+			parm64[i].u.pointer.size = parm32[i].u.pointer.size;
+			parm64[i].u.pointer.u.linear_addr =
+			    parm32[i].u.pointer.u.linear_addr;
+			break;
+
+		default:
+			ret = -EINVAL;
+		}
+		if (ret < 0)
+			goto out_free;
+	}
+
+	ret = vbg_hgcm_call(gdev, requestor, client_id, function, timeout_ms,
+			    parm64, parm_count, vbox_status);
+	if (ret < 0)
+		goto out_free;
+
+	/* Copy back. */
+	for (i = 0; i < parm_count; i++, parm32++, parm64++) {
+		switch (parm64[i].type) {
+		case VMMDEV_HGCM_PARM_TYPE_32BIT:
+			parm32[i].u.value32 = parm64[i].u.value32;
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_64BIT:
+			parm32[i].u.value64 = parm64[i].u.value64;
+			break;
+
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_OUT:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR:
+		case VMMDEV_HGCM_PARM_TYPE_LINADDR_IN:
+			parm32[i].u.pointer.size = parm64[i].u.pointer.size;
+			break;
+
+		default:
+			WARN_ON(1);
+			ret = -EINVAL;
+		}
+	}
+
+out_free:
+	kfree(parm64);
+	return ret;
+}
+#endif
+
+static const int vbg_status_code_to_errno_table[] = {
+	[-VERR_ACCESS_DENIED]                            = -EPERM,
+	[-VERR_FILE_NOT_FOUND]                           = -ENOENT,
+	[-VERR_PROCESS_NOT_FOUND]                        = -ESRCH,
+	[-VERR_INTERRUPTED]                              = -EINTR,
+	[-VERR_DEV_IO_ERROR]                             = -EIO,
+	[-VERR_TOO_MUCH_DATA]                            = -E2BIG,
+	[-VERR_BAD_EXE_FORMAT]                           = -ENOEXEC,
+	[-VERR_INVALID_HANDLE]                           = -EBADF,
+	[-VERR_TRY_AGAIN]                                = -EAGAIN,
+	[-VERR_NO_MEMORY]                                = -ENOMEM,
+	[-VERR_INVALID_POINTER]                          = -EFAULT,
+	[-VERR_RESOURCE_BUSY]                            = -EBUSY,
+	[-VERR_ALREADY_EXISTS]                           = -EEXIST,
+	[-VERR_NOT_SAME_DEVICE]                          = -EXDEV,
+	[-VERR_NOT_A_DIRECTORY]                          = -ENOTDIR,
+	[-VERR_PATH_NOT_FOUND]                           = -ENOTDIR,
+	[-VERR_INVALID_NAME]                             = -ENOENT,
+	[-VERR_IS_A_DIRECTORY]                           = -EISDIR,
+	[-VERR_INVALID_PARAMETER]                        = -EINVAL,
+	[-VERR_TOO_MANY_OPEN_FILES]                      = -ENFILE,
+	[-VERR_INVALID_FUNCTION]                         = -ENOTTY,
+	[-VERR_SHARING_VIOLATION]                        = -ETXTBSY,
+	[-VERR_FILE_TOO_BIG]                             = -EFBIG,
+	[-VERR_DISK_FULL]                                = -ENOSPC,
+	[-VERR_SEEK_ON_DEVICE]                           = -ESPIPE,
+	[-VERR_WRITE_PROTECT]                            = -EROFS,
+	[-VERR_BROKEN_PIPE]                              = -EPIPE,
+	[-VERR_DEADLOCK]                                 = -EDEADLK,
+	[-VERR_FILENAME_TOO_LONG]                        = -ENAMETOOLONG,
+	[-VERR_FILE_LOCK_FAILED]                         = -ENOLCK,
+	[-VERR_NOT_IMPLEMENTED]                          = -ENOSYS,
+	[-VERR_NOT_SUPPORTED]                            = -ENOSYS,
+	[-VERR_DIR_NOT_EMPTY]                            = -ENOTEMPTY,
+	[-VERR_TOO_MANY_SYMLINKS]                        = -ELOOP,
+	[-VERR_NO_MORE_FILES]				 = -ENODATA,
+	[-VERR_NO_DATA]                                  = -ENODATA,
+	[-VERR_NET_NO_NETWORK]                           = -ENONET,
+	[-VERR_NET_NOT_UNIQUE_NAME]                      = -ENOTUNIQ,
+	[-VERR_NO_TRANSLATION]                           = -EILSEQ,
+	[-VERR_NET_NOT_SOCKET]                           = -ENOTSOCK,
+	[-VERR_NET_DEST_ADDRESS_REQUIRED]                = -EDESTADDRREQ,
+	[-VERR_NET_MSG_SIZE]                             = -EMSGSIZE,
+	[-VERR_NET_PROTOCOL_TYPE]                        = -EPROTOTYPE,
+	[-VERR_NET_PROTOCOL_NOT_AVAILABLE]               = -ENOPROTOOPT,
+	[-VERR_NET_PROTOCOL_NOT_SUPPORTED]               = -EPROTONOSUPPORT,
+	[-VERR_NET_SOCKET_TYPE_NOT_SUPPORTED]            = -ESOCKTNOSUPPORT,
+	[-VERR_NET_OPERATION_NOT_SUPPORTED]              = -EOPNOTSUPP,
+	[-VERR_NET_PROTOCOL_FAMILY_NOT_SUPPORTED]        = -EPFNOSUPPORT,
+	[-VERR_NET_ADDRESS_FAMILY_NOT_SUPPORTED]         = -EAFNOSUPPORT,
+	[-VERR_NET_ADDRESS_IN_USE]                       = -EADDRINUSE,
+	[-VERR_NET_ADDRESS_NOT_AVAILABLE]                = -EADDRNOTAVAIL,
+	[-VERR_NET_DOWN]                                 = -ENETDOWN,
+	[-VERR_NET_UNREACHABLE]                          = -ENETUNREACH,
+	[-VERR_NET_CONNECTION_RESET]                     = -ENETRESET,
+	[-VERR_NET_CONNECTION_ABORTED]                   = -ECONNABORTED,
+	[-VERR_NET_CONNECTION_RESET_BY_PEER]             = -ECONNRESET,
+	[-VERR_NET_NO_BUFFER_SPACE]                      = -ENOBUFS,
+	[-VERR_NET_ALREADY_CONNECTED]                    = -EISCONN,
+	[-VERR_NET_NOT_CONNECTED]                        = -ENOTCONN,
+	[-VERR_NET_SHUTDOWN]                             = -ESHUTDOWN,
+	[-VERR_NET_TOO_MANY_REFERENCES]                  = -ETOOMANYREFS,
+	[-VERR_TIMEOUT]                                  = -ETIMEDOUT,
+	[-VERR_NET_CONNECTION_REFUSED]                   = -ECONNREFUSED,
+	[-VERR_NET_HOST_DOWN]                            = -EHOSTDOWN,
+	[-VERR_NET_HOST_UNREACHABLE]                     = -EHOSTUNREACH,
+	[-VERR_NET_ALREADY_IN_PROGRESS]                  = -EALREADY,
+	[-VERR_NET_IN_PROGRESS]                          = -EINPROGRESS,
+	[-VERR_MEDIA_NOT_PRESENT]                        = -ENOMEDIUM,
+	[-VERR_MEDIA_NOT_RECOGNIZED]                     = -EMEDIUMTYPE,
+};
+
+int vbg_status_code_to_errno(int rc)
+{
+	if (rc >= 0)
+		return 0;
+
+	rc = -rc;
+	if (rc >= ARRAY_SIZE(vbg_status_code_to_errno_table) ||
+	    vbg_status_code_to_errno_table[rc] == 0) {
+		vbg_warn("%s: Unhandled err %d\n", __func__, -rc);
+		return -EPROTO;
+	}
+
+	return vbg_status_code_to_errno_table[rc];
+}
+EXPORT_SYMBOL(vbg_status_code_to_errno);

linux-7.2.3/drivers/virt/vboxguest/vboxguest_version.h

@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */
+/*
+ * VBox Guest additions version info, this is used by the host to determine
+ * supported guest-addition features in some cases. So this will need to be
+ * synced with vbox upstreams versioning scheme when we implement / port
+ * new features from the upstream out-of-tree vboxguest driver.
+ */
+
+#ifndef __VBOX_VERSION_H__
+#define __VBOX_VERSION_H__
+
+#define VBG_VERSION_MAJOR 6
+#define VBG_VERSION_MINOR 0
+#define VBG_VERSION_BUILD 0
+#define VBG_SVN_REV 127566
+#define VBG_VERSION_STRING "6.0.0"
+
+#endif

linux-7.2.3/drivers/virt/vboxguest/vmmdev.h

@@ -0,0 +1,453 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */
+/*
+ * Virtual Device for Guest <-> VMM/Host communication interface
+ *
+ * Copyright (C) 2006-2016 Oracle Corporation
+ */
+
+#ifndef __VBOX_VMMDEV_H__
+#define __VBOX_VMMDEV_H__
+
+#include <asm/bitsperlong.h>
+#include <linux/sizes.h>
+#include <linux/types.h>
+#include <linux/vbox_vmmdev_types.h>
+
+/* Port for generic request interface (relative offset). */
+#define VMMDEV_PORT_OFF_REQUEST                             0
+
+/** Layout of VMMDEV RAM region that contains information for guest. */
+struct vmmdev_memory {
+	/** The size of this structure. */
+	u32 size;
+	/** The structure version. (VMMDEV_MEMORY_VERSION) */
+	u32 version;
+
+	union {
+		struct {
+			/** Flag telling that VMMDev has events pending. */
+			u8 have_events;
+			/** Explicit padding, MBZ. */
+			u8 padding[3];
+		} V1_04;
+
+		struct {
+			/** Pending events flags, set by host. */
+			u32 host_events;
+			/** Mask of events the guest wants, set by guest. */
+			u32 guest_event_mask;
+		} V1_03;
+	} V;
+
+	/* struct vbva_memory, not used */
+};
+VMMDEV_ASSERT_SIZE(vmmdev_memory, 8 + 8);
+
+/** Version of vmmdev_memory structure (vmmdev_memory::version). */
+#define VMMDEV_MEMORY_VERSION   (1)
+
+/* Host mouse capabilities has been changed. */
+#define VMMDEV_EVENT_MOUSE_CAPABILITIES_CHANGED             BIT(0)
+/* HGCM event. */
+#define VMMDEV_EVENT_HGCM                                   BIT(1)
+/* A display change request has been issued. */
+#define VMMDEV_EVENT_DISPLAY_CHANGE_REQUEST                 BIT(2)
+/* Credentials are available for judgement. */
+#define VMMDEV_EVENT_JUDGE_CREDENTIALS                      BIT(3)
+/* The guest has been restored. */
+#define VMMDEV_EVENT_RESTORED                               BIT(4)
+/* Seamless mode state changed. */
+#define VMMDEV_EVENT_SEAMLESS_MODE_CHANGE_REQUEST           BIT(5)
+/* Memory balloon size changed. */
+#define VMMDEV_EVENT_BALLOON_CHANGE_REQUEST                 BIT(6)
+/* Statistics interval changed. */
+#define VMMDEV_EVENT_STATISTICS_INTERVAL_CHANGE_REQUEST     BIT(7)
+/* VRDP status changed. */
+#define VMMDEV_EVENT_VRDP                                   BIT(8)
+/* New mouse position data available. */
+#define VMMDEV_EVENT_MOUSE_POSITION_CHANGED                 BIT(9)
+/* CPU hotplug event occurred. */
+#define VMMDEV_EVENT_CPU_HOTPLUG                            BIT(10)
+/* The mask of valid events, for sanity checking. */
+#define VMMDEV_EVENT_VALID_EVENT_MASK                       0x000007ffU
+
+/*
+ * Additions are allowed to work only if additions_major == vmmdev_current &&
+ * additions_minor <= vmmdev_current. Additions version is reported to host
+ * (VMMDev) by VMMDEVREQ_REPORT_GUEST_INFO.
+ */
+#define VMMDEV_VERSION                      0x00010004
+#define VMMDEV_VERSION_MAJOR                (VMMDEV_VERSION >> 16)
+#define VMMDEV_VERSION_MINOR                (VMMDEV_VERSION & 0xffff)
+
+/* Maximum request packet size. */
+#define VMMDEV_MAX_VMMDEVREQ_SIZE           1048576
+
+/* Version of vmmdev_request_header structure. */
+#define VMMDEV_REQUEST_HEADER_VERSION       0x10001
+
+/** struct vmmdev_request_header - Generic VMMDev request header. */
+struct vmmdev_request_header {
+	/** IN: Size of the structure in bytes (including body). */
+	u32 size;
+	/** IN: Version of the structure.  */
+	u32 version;
+	/** IN: Type of the request. */
+	enum vmmdev_request_type request_type;
+	/** OUT: Return code. */
+	s32 rc;
+	/** Reserved field no.1. MBZ. */
+	u32 reserved1;
+	/** IN: Requestor information (VMMDEV_REQUESTOR_*) */
+	u32 requestor;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_request_header, 24);
+
+/**
+ * struct vmmdev_mouse_status - Mouse status request structure.
+ *
+ * Used by VMMDEVREQ_GET_MOUSE_STATUS and VMMDEVREQ_SET_MOUSE_STATUS.
+ */
+struct vmmdev_mouse_status {
+	/** header */
+	struct vmmdev_request_header header;
+	/** Mouse feature mask. See VMMDEV_MOUSE_*. */
+	u32 mouse_features;
+	/** Mouse x position. */
+	s32 pointer_pos_x;
+	/** Mouse y position. */
+	s32 pointer_pos_y;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_mouse_status, 24 + 12);
+
+/* The guest can (== wants to) handle absolute coordinates.  */
+#define VMMDEV_MOUSE_GUEST_CAN_ABSOLUTE                     BIT(0)
+/*
+ * The host can (== wants to) send absolute coordinates.
+ * (Input not captured.)
+ */
+#define VMMDEV_MOUSE_HOST_WANTS_ABSOLUTE                    BIT(1)
+/*
+ * The guest can *NOT* switch to software cursor and therefore depends on the
+ * host cursor.
+ *
+ * When guest additions are installed and the host has promised to display the
+ * cursor itself, the guest installs a hardware mouse driver. Don't ask the
+ * guest to switch to a software cursor then.
+ */
+#define VMMDEV_MOUSE_GUEST_NEEDS_HOST_CURSOR                BIT(2)
+/* The host does NOT provide support for drawing the cursor itself. */
+#define VMMDEV_MOUSE_HOST_CANNOT_HWPOINTER                  BIT(3)
+/* The guest can read VMMDev events to find out about pointer movement */
+#define VMMDEV_MOUSE_NEW_PROTOCOL                           BIT(4)
+/*
+ * If the guest changes the status of the VMMDEV_MOUSE_GUEST_NEEDS_HOST_CURSOR
+ * bit, the host will honour this.
+ */
+#define VMMDEV_MOUSE_HOST_RECHECKS_NEEDS_HOST_CURSOR        BIT(5)
+/*
+ * The host supplies an absolute pointing device.  The Guest Additions may
+ * wish to use this to decide whether to install their own driver.
+ */
+#define VMMDEV_MOUSE_HOST_HAS_ABS_DEV                       BIT(6)
+
+/* The minimum value our pointing device can return. */
+#define VMMDEV_MOUSE_RANGE_MIN 0
+/* The maximum value our pointing device can return. */
+#define VMMDEV_MOUSE_RANGE_MAX 0xFFFF
+
+/**
+ * struct vmmdev_host_version - VirtualBox host version request structure.
+ *
+ * VBG uses this to detect the precense of new features in the interface.
+ */
+struct vmmdev_host_version {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** Major version. */
+	u16 major;
+	/** Minor version. */
+	u16 minor;
+	/** Build number. */
+	u32 build;
+	/** SVN revision. */
+	u32 revision;
+	/** Feature mask. */
+	u32 features;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_host_version, 24 + 16);
+
+/* Physical page lists are supported by HGCM. */
+#define VMMDEV_HVF_HGCM_PHYS_PAGE_LIST  BIT(0)
+
+/**
+ * struct vmmdev_mask - Structure to set / clear bits in a mask used for
+ * VMMDEVREQ_SET_GUEST_CAPABILITIES and VMMDEVREQ_CTL_GUEST_FILTER_MASK.
+ */
+struct vmmdev_mask {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** Mask of bits to be set. */
+	u32 or_mask;
+	/** Mask of bits to be cleared. */
+	u32 not_mask;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_mask, 24 + 8);
+
+/* The guest supports seamless display rendering. */
+#define VMMDEV_GUEST_SUPPORTS_SEAMLESS                      BIT(0)
+/* The guest supports mapping guest to host windows. */
+#define VMMDEV_GUEST_SUPPORTS_GUEST_HOST_WINDOW_MAPPING     BIT(1)
+/*
+ * The guest graphical additions are active.
+ * Used for fast activation and deactivation of certain graphical operations
+ * (e.g. resizing & seamless). The legacy VMMDEVREQ_REPORT_GUEST_CAPABILITIES
+ * request sets this automatically, but VMMDEVREQ_SET_GUEST_CAPABILITIES does
+ * not.
+ */
+#define VMMDEV_GUEST_SUPPORTS_GRAPHICS                      BIT(2)
+/* The mask of valid capabilities, for sanity checking. */
+#define VMMDEV_GUEST_CAPABILITIES_MASK                      0x00000007U
+
+/** struct vmmdev_hypervisorinfo - Hypervisor info structure. */
+struct vmmdev_hypervisorinfo {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/**
+	 * Guest virtual address of proposed hypervisor start.
+	 * Not used by VMMDEVREQ_GET_HYPERVISOR_INFO.
+	 */
+	u32 hypervisor_start;
+	/** Hypervisor size in bytes. */
+	u32 hypervisor_size;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_hypervisorinfo, 24 + 8);
+
+/** struct vmmdev_events - Pending events structure. */
+struct vmmdev_events {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** OUT: Pending event mask. */
+	u32 events;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_events, 24 + 4);
+
+#define VMMDEV_OSTYPE_LINUX26		0x53000
+#define VMMDEV_OSTYPE_X64		BIT(8)
+
+/** struct vmmdev_guestinfo - Guest information report. */
+struct vmmdev_guest_info {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/**
+	 * The VMMDev interface version expected by additions.
+	 * *Deprecated*, do not use anymore! Will be removed.
+	 */
+	u32 interface_version;
+	/** Guest OS type. */
+	u32 os_type;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_guest_info, 24 + 8);
+
+#define VMMDEV_GUEST_INFO2_ADDITIONS_FEATURES_REQUESTOR_INFO	BIT(0)
+
+/** struct vmmdev_guestinfo2 - Guest information report, version 2. */
+struct vmmdev_guest_info2 {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** Major version. */
+	u16 additions_major;
+	/** Minor version. */
+	u16 additions_minor;
+	/** Build number. */
+	u32 additions_build;
+	/** SVN revision. */
+	u32 additions_revision;
+	/** Feature mask. */
+	u32 additions_features;
+	/**
+	 * The intentional meaning of this field was:
+	 * Some additional information, for example 'Beta 1' or something like
+	 * that.
+	 *
+	 * The way it was implemented was implemented: VBG_VERSION_STRING.
+	 *
+	 * This means the first three members are duplicated in this field (if
+	 * the guest build config is sane). So, the user must check this and
+	 * chop it off before usage. There is, because of the Main code's blind
+	 * trust in the field's content, no way back.
+	 */
+	char name[128];
+};
+VMMDEV_ASSERT_SIZE(vmmdev_guest_info2, 24 + 144);
+
+enum vmmdev_guest_facility_type {
+	VBOXGUEST_FACILITY_TYPE_UNKNOWN          = 0,
+	VBOXGUEST_FACILITY_TYPE_VBOXGUEST_DRIVER = 20,
+	/* VBoxGINA / VBoxCredProv / pam_vbox. */
+	VBOXGUEST_FACILITY_TYPE_AUTO_LOGON       = 90,
+	VBOXGUEST_FACILITY_TYPE_VBOX_SERVICE     = 100,
+	/* VBoxTray (Windows), VBoxClient (Linux, Unix). */
+	VBOXGUEST_FACILITY_TYPE_VBOX_TRAY_CLIENT = 101,
+	VBOXGUEST_FACILITY_TYPE_SEAMLESS         = 1000,
+	VBOXGUEST_FACILITY_TYPE_GRAPHICS         = 1100,
+	VBOXGUEST_FACILITY_TYPE_ALL              = 0x7ffffffe,
+	/* Ensure the enum is a 32 bit data-type */
+	VBOXGUEST_FACILITY_TYPE_SIZEHACK         = 0x7fffffff
+};
+
+enum vmmdev_guest_facility_status {
+	VBOXGUEST_FACILITY_STATUS_INACTIVE    = 0,
+	VBOXGUEST_FACILITY_STATUS_PAUSED      = 1,
+	VBOXGUEST_FACILITY_STATUS_PRE_INIT    = 20,
+	VBOXGUEST_FACILITY_STATUS_INIT        = 30,
+	VBOXGUEST_FACILITY_STATUS_ACTIVE      = 50,
+	VBOXGUEST_FACILITY_STATUS_TERMINATING = 100,
+	VBOXGUEST_FACILITY_STATUS_TERMINATED  = 101,
+	VBOXGUEST_FACILITY_STATUS_FAILED      = 800,
+	VBOXGUEST_FACILITY_STATUS_UNKNOWN     = 999,
+	/* Ensure the enum is a 32 bit data-type */
+	VBOXGUEST_FACILITY_STATUS_SIZEHACK    = 0x7fffffff
+};
+
+/** struct vmmdev_guest_status - Guest Additions status structure. */
+struct vmmdev_guest_status {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** Facility the status is indicated for. */
+	enum vmmdev_guest_facility_type facility;
+	/** Current guest status. */
+	enum vmmdev_guest_facility_status status;
+	/** Flags, not used at the moment. */
+	u32 flags;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_guest_status, 24 + 12);
+
+#define VMMDEV_MEMORY_BALLOON_CHUNK_SIZE             (1048576)
+#define VMMDEV_MEMORY_BALLOON_CHUNK_PAGES            (1048576 / 4096)
+
+/** struct vmmdev_memballoon_info - Memory-balloon info structure. */
+struct vmmdev_memballoon_info {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** Balloon size in megabytes. */
+	u32 balloon_chunks;
+	/** Guest ram size in megabytes. */
+	u32 phys_mem_chunks;
+	/**
+	 * Setting this to VMMDEV_EVENT_BALLOON_CHANGE_REQUEST indicates that
+	 * the request is a response to that event.
+	 * (Don't confuse this with VMMDEVREQ_ACKNOWLEDGE_EVENTS.)
+	 */
+	u32 event_ack;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_memballoon_info, 24 + 12);
+
+/** struct vmmdev_memballoon_change - Change the size of the balloon. */
+struct vmmdev_memballoon_change {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** The number of pages in the array. */
+	u32 pages;
+	/** true = inflate, false = deflate.  */
+	u32 inflate;
+	/** Physical address (u64) of each page. */
+	u64 phys_page[VMMDEV_MEMORY_BALLOON_CHUNK_PAGES];
+};
+
+/** struct vmmdev_write_core_dump - Write Core Dump request data. */
+struct vmmdev_write_core_dump {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** Flags (reserved, MBZ). */
+	u32 flags;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_write_core_dump, 24 + 4);
+
+/** struct vmmdev_heartbeat - Heart beat check state structure. */
+struct vmmdev_heartbeat {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** OUT: Guest heartbeat interval in nanosec. */
+	u64 interval_ns;
+	/** Heartbeat check flag. */
+	u8 enabled;
+	/** Explicit padding, MBZ. */
+	u8 padding[3];
+} __packed;
+VMMDEV_ASSERT_SIZE(vmmdev_heartbeat, 24 + 12);
+
+#define VMMDEV_HGCM_REQ_DONE      BIT(0)
+#define VMMDEV_HGCM_REQ_CANCELLED BIT(1)
+
+/** struct vmmdev_hgcmreq_header - vmmdev HGCM requests header. */
+struct vmmdev_hgcmreq_header {
+	/** Request header. */
+	struct vmmdev_request_header header;
+
+	/** HGCM flags. */
+	u32 flags;
+
+	/** Result code. */
+	s32 result;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_hgcmreq_header, 24 + 8);
+
+/** struct vmmdev_hgcm_connect - HGCM connect request structure. */
+struct vmmdev_hgcm_connect {
+	/** HGCM request header. */
+	struct vmmdev_hgcmreq_header header;
+
+	/** IN: Description of service to connect to. */
+	struct vmmdev_hgcm_service_location loc;
+
+	/** OUT: Client identifier assigned by local instance of HGCM. */
+	u32 client_id;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_hgcm_connect, 32 + 132 + 4);
+
+/** struct vmmdev_hgcm_disconnect - HGCM disconnect request structure. */
+struct vmmdev_hgcm_disconnect {
+	/** HGCM request header. */
+	struct vmmdev_hgcmreq_header header;
+
+	/** IN: Client identifier. */
+	u32 client_id;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_hgcm_disconnect, 32 + 4);
+
+#define VMMDEV_HGCM_MAX_PARMS 32
+
+/** struct vmmdev_hgcm_call - HGCM call request structure. */
+struct vmmdev_hgcm_call {
+	/* request header */
+	struct vmmdev_hgcmreq_header header;
+
+	/** IN: Client identifier. */
+	u32 client_id;
+	/** IN: Service function number. */
+	u32 function;
+	/** IN: Number of parameters. */
+	u32 parm_count;
+	/** Parameters follow in form: HGCMFunctionParameter32|64 parms[X]; */
+};
+VMMDEV_ASSERT_SIZE(vmmdev_hgcm_call, 32 + 12);
+
+/**
+ * struct vmmdev_hgcm_cancel2 - HGCM cancel request structure, version 2.
+ *
+ * After the request header.rc will be:
+ *
+ * VINF_SUCCESS when cancelled.
+ * VERR_NOT_FOUND if the specified request cannot be found.
+ * VERR_INVALID_PARAMETER if the address is invalid valid.
+ */
+struct vmmdev_hgcm_cancel2 {
+	/** Header. */
+	struct vmmdev_request_header header;
+	/** The physical address of the request to cancel. */
+	u32 phys_req_to_cancel;
+};
+VMMDEV_ASSERT_SIZE(vmmdev_hgcm_cancel2, 24 + 4);
+
+#endif

linux-7.2.3/drivers/virt/vmgenid.c

@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2022 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
+ *
+ * The "Virtual Machine Generation ID" is exposed via ACPI or DT and changes when a
+ * virtual machine forks or is cloned. This driver exists for shepherding that
+ * information to random.c.
+ */
+
+#include <linux/acpi.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/random.h>
+
+ACPI_MODULE_NAME("vmgenid");
+
+enum { VMGENID_SIZE = 16 };
+
+struct vmgenid_state {
+	u8 *next_id;
+	u8 this_id[VMGENID_SIZE];
+};
+
+static void vmgenid_notify(struct device *device)
+{
+	struct vmgenid_state *state = device->driver_data;
+	u8 old_id[VMGENID_SIZE];
+
+	memcpy(old_id, state->this_id, sizeof(old_id));
+	memcpy(state->this_id, state->next_id, sizeof(state->this_id));
+	if (!memcmp(old_id, state->this_id, sizeof(old_id)))
+		return;
+	add_vmfork_randomness(state->this_id, sizeof(state->this_id));
+}
+
+static void setup_vmgenid_state(struct vmgenid_state *state, void *virt_addr)
+{
+	state->next_id = virt_addr;
+	memcpy(state->this_id, state->next_id, sizeof(state->this_id));
+	add_device_randomness(state->this_id, sizeof(state->this_id));
+}
+
+#ifdef CONFIG_ACPI
+static void vmgenid_acpi_handler(acpi_handle __always_unused handle,
+				 u32 __always_unused event, void *dev)
+{
+	vmgenid_notify(dev);
+}
+
+static int vmgenid_add_acpi(struct device *dev, struct vmgenid_state *state)
+{
+	struct acpi_device *device = ACPI_COMPANION(dev);
+	struct acpi_buffer parsed = { ACPI_ALLOCATE_BUFFER };
+	union acpi_object *obj;
+	phys_addr_t phys_addr;
+	acpi_status status;
+	void *virt_addr;
+	int ret = 0;
+
+	status = acpi_evaluate_object(device->handle, "ADDR", NULL, &parsed);
+	if (ACPI_FAILURE(status)) {
+		ACPI_EXCEPTION((AE_INFO, status, "Evaluating ADDR"));
+		return -ENODEV;
+	}
+	obj = parsed.pointer;
+	if (!obj || obj->type != ACPI_TYPE_PACKAGE || obj->package.count != 2 ||
+	    obj->package.elements[0].type != ACPI_TYPE_INTEGER ||
+	    obj->package.elements[1].type != ACPI_TYPE_INTEGER) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	phys_addr = (obj->package.elements[0].integer.value << 0) |
+		    (obj->package.elements[1].integer.value << 32);
+
+	virt_addr = devm_memremap(&device->dev, phys_addr, VMGENID_SIZE, MEMREMAP_WB);
+	if (IS_ERR(virt_addr)) {
+		ret = PTR_ERR(virt_addr);
+		goto out;
+	}
+	setup_vmgenid_state(state, virt_addr);
+
+	status = acpi_install_notify_handler(device->handle, ACPI_DEVICE_NOTIFY,
+					     vmgenid_acpi_handler, dev);
+	if (ACPI_FAILURE(status)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	dev->driver_data = state;
+out:
+	ACPI_FREE(parsed.pointer);
+	return ret;
+}
+#else
+static int vmgenid_add_acpi(struct device *dev, struct vmgenid_state *state)
+{
+	return -EINVAL;
+}
+#endif
+
+static irqreturn_t vmgenid_of_irq_handler(int __always_unused irq, void *dev)
+{
+	vmgenid_notify(dev);
+	return IRQ_HANDLED;
+}
+
+static int vmgenid_add_of(struct platform_device *pdev,
+			  struct vmgenid_state *state)
+{
+	void *virt_addr;
+	int ret;
+
+	virt_addr = devm_platform_get_and_ioremap_resource(pdev, 0, NULL);
+	if (IS_ERR(virt_addr))
+		return PTR_ERR(virt_addr);
+
+	setup_vmgenid_state(state, virt_addr);
+
+	ret = platform_get_irq(pdev, 0);
+	if (ret < 0)
+		return ret;
+
+	ret = devm_request_irq(&pdev->dev, ret, vmgenid_of_irq_handler,
+			       IRQF_SHARED, "vmgenid", &pdev->dev);
+	if (ret < 0)
+		return ret;
+
+	pdev->dev.driver_data = state;
+	return 0;
+}
+
+static int vmgenid_add(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct vmgenid_state *state;
+	int ret;
+
+	state = devm_kmalloc(dev, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return -ENOMEM;
+
+	if (dev->of_node)
+		ret = vmgenid_add_of(pdev, state);
+	else
+		ret = vmgenid_add_acpi(dev, state);
+
+	if (ret < 0)
+		devm_kfree(dev, state);
+	return ret;
+}
+
+static const struct of_device_id vmgenid_of_ids[] = {
+	{ .compatible = "microsoft,vmgenid", },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, vmgenid_of_ids);
+
+static const struct acpi_device_id vmgenid_acpi_ids[] = {
+	{ "VMGENCTR", 0 },
+	{ "VM_GEN_COUNTER", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, vmgenid_acpi_ids);
+
+static struct platform_driver vmgenid_plaform_driver = {
+	.probe      = vmgenid_add,
+	.driver     = {
+		.name   = "vmgenid",
+		.acpi_match_table = vmgenid_acpi_ids,
+		.of_match_table = vmgenid_of_ids,
+	},
+};
+
+module_platform_driver(vmgenid_plaform_driver)
+
+MODULE_DESCRIPTION("Virtual Machine Generation ID");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");