Resguardo inicial

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;
+}