summaryrefslogtreecommitdiffstats
path: root/drivers/virt
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-07 18:49:45 +0000
commit2c3c1048746a4622d8c89a29670120dc8fab93c4 (patch)
tree848558de17fb3008cdf4d861b01ac7781903ce39 /drivers/virt
parentInitial commit. (diff)
downloadlinux-2c3c1048746a4622d8c89a29670120dc8fab93c4.tar.xz
linux-2c3c1048746a4622d8c89a29670120dc8fab93c4.zip
Adding upstream version 6.1.76.upstream/6.1.76
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'drivers/virt')
-rw-r--r--drivers/virt/Kconfig55
-rw-r--r--drivers/virt/Makefile13
-rw-r--r--drivers/virt/acrn/Kconfig15
-rw-r--r--drivers/virt/acrn/Makefile3
-rw-r--r--drivers/virt/acrn/acrn_drv.h229
-rw-r--r--drivers/virt/acrn/hsm.c538
-rw-r--r--drivers/virt/acrn/hypercall.h306
-rw-r--r--drivers/virt/acrn/ioeventfd.c273
-rw-r--r--drivers/virt/acrn/ioreq.c652
-rw-r--r--drivers/virt/acrn/irqfd.c234
-rw-r--r--drivers/virt/acrn/mm.c329
-rw-r--r--drivers/virt/acrn/vm.c126
-rw-r--r--drivers/virt/coco/efi_secret/Kconfig16
-rw-r--r--drivers/virt/coco/efi_secret/Makefile2
-rw-r--r--drivers/virt/coco/efi_secret/efi_secret.c349
-rw-r--r--drivers/virt/coco/sev-guest/Kconfig15
-rw-r--r--drivers/virt/coco/sev-guest/Makefile2
-rw-r--r--drivers/virt/coco/sev-guest/sev-guest.c875
-rw-r--r--drivers/virt/coco/sev-guest/sev-guest.h63
-rw-r--r--drivers/virt/fsl_hypervisor.c932
-rw-r--r--drivers/virt/nitro_enclaves/Kconfig26
-rw-r--r--drivers/virt/nitro_enclaves/Makefile9
-rw-r--r--drivers/virt/nitro_enclaves/ne_misc_dev.c1783
-rw-r--r--drivers/virt/nitro_enclaves/ne_misc_dev.h109
-rw-r--r--drivers/virt/nitro_enclaves/ne_misc_dev_test.c154
-rw-r--r--drivers/virt/nitro_enclaves/ne_pci_dev.c626
-rw-r--r--drivers/virt/nitro_enclaves/ne_pci_dev.h331
-rw-r--r--drivers/virt/vboxguest/Kconfig19
-rw-r--r--drivers/virt/vboxguest/Makefile4
-rw-r--r--drivers/virt/vboxguest/vboxguest_core.c1826
-rw-r--r--drivers/virt/vboxguest/vboxguest_core.h214
-rw-r--r--drivers/virt/vboxguest/vboxguest_linux.c500
-rw-r--r--drivers/virt/vboxguest/vboxguest_utils.c825
-rw-r--r--drivers/virt/vboxguest/vboxguest_version.h18
-rw-r--r--drivers/virt/vboxguest/vmmdev.h453
-rw-r--r--drivers/virt/vmgenid.c101
36 files changed, 12025 insertions, 0 deletions
diff --git a/drivers/virt/Kconfig b/drivers/virt/Kconfig
new file mode 100644
index 000000000..87ef258ce
--- /dev/null
+++ b/drivers/virt/Kconfig
@@ -0,0 +1,55 @@
+# 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
+ depends on ACPI
+ 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"
+
+source "drivers/virt/coco/efi_secret/Kconfig"
+
+source "drivers/virt/coco/sev-guest/Kconfig"
+
+endif
diff --git a/drivers/virt/Makefile b/drivers/virt/Makefile
new file mode 100644
index 000000000..093674e05
--- /dev/null
+++ b/drivers/virt/Makefile
@@ -0,0 +1,13 @@
+# 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-$(CONFIG_EFI_SECRET) += coco/efi_secret/
+obj-$(CONFIG_SEV_GUEST) += coco/sev-guest/
diff --git a/drivers/virt/acrn/Kconfig b/drivers/virt/acrn/Kconfig
new file mode 100644
index 000000000..3e1a61c9d
--- /dev/null
+++ b/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.
diff --git a/drivers/virt/acrn/Makefile b/drivers/virt/acrn/Makefile
new file mode 100644
index 000000000..08ce641dc
--- /dev/null
+++ b/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
diff --git a/drivers/virt/acrn/acrn_drv.h b/drivers/virt/acrn/acrn_drv.h
new file mode 100644
index 000000000..5663c17ad
--- /dev/null
+++ b/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[];
+};
+
+/**
+ * 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 */
diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c
new file mode 100644
index 000000000..423ea888d
--- /dev/null
+++ b/drivers/virt/acrn/hsm.c
@@ -0,0 +1,538 @@
+// 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/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(sizeof(*vm), GFP_KERNEL);
+ 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 = kmalloc(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 = kmalloc(sizeof(*px_data), GFP_KERNEL);
+ 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 = kmalloc(sizeof(*cx_data), GFP_KERNEL);
+ 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).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)");
diff --git a/drivers/virt/acrn/hypercall.h b/drivers/virt/acrn/hypercall.h
new file mode 100644
index 000000000..71d300821
--- /dev/null
+++ b/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 */
diff --git a/drivers/virt/acrn/ioeventfd.c b/drivers/virt/acrn/ioeventfd.c
new file mode 100644
index 000000000..ac4037e9f
--- /dev/null
+++ b/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(sizeof(*p), GFP_KERNEL);
+ 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, 1);
+ 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);
+}
diff --git a/drivers/virt/acrn/ioreq.c b/drivers/virt/acrn/ioreq.c
new file mode 100644
index 000000000..d75ab3f66
--- /dev/null
+++ b/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(sizeof(*range), GFP_KERNEL);
+ 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 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 (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(sizeof(*client), GFP_KERNEL);
+ if (!client)
+ return NULL;
+
+ client->handler = handler;
+ client->vm = vm;
+ client->priv = priv;
+ client->is_default = is_default;
+ if (name)
+ strncpy(client->name, name, sizeof(client->name) - 1);
+ 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_workqueue("ioreq_wq",
+ WQ_HIGHPRI | WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
+ 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(sizeof(*set_buffer), GFP_KERNEL);
+ 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 %pK!\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 %pK!\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;
+ }
+}
diff --git a/drivers/virt/acrn/irqfd.c b/drivers/virt/acrn/irqfd.c
new file mode 100644
index 000000000..d4ad211dc
--- /dev/null
+++ b/drivers/virt/acrn/irqfd.c
@@ -0,0 +1,234 @@
+// 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"
+
+static LIST_HEAD(acrn_irqfd_clients);
+
+/**
+ * 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
+ */
+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;
+};
+
+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);
+}
+
+static void hsm_irqfd_shutdown(struct hsm_irqfd *irqfd)
+{
+ u64 cnt;
+
+ lockdep_assert_held(&irqfd->vm->irqfds_lock);
+
+ /* remove from wait queue */
+ list_del_init(&irqfd->list);
+ eventfd_ctx_remove_wait_queue(irqfd->eventfd, &irqfd->wait, &cnt);
+ eventfd_ctx_put(irqfd->eventfd);
+ kfree(irqfd);
+}
+
+static void hsm_irqfd_shutdown_work(struct work_struct *work)
+{
+ struct hsm_irqfd *irqfd;
+ struct acrn_vm *vm;
+
+ irqfd = container_of(work, struct hsm_irqfd, shutdown);
+ vm = irqfd->vm;
+ mutex_lock(&vm->irqfds_lock);
+ if (!list_empty(&irqfd->list))
+ hsm_irqfd_shutdown(irqfd);
+ mutex_unlock(&vm->irqfds_lock);
+}
+
+/* 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;
+ struct acrn_vm *vm;
+
+ irqfd = container_of(wait, struct hsm_irqfd, wait);
+ vm = irqfd->vm;
+ if (poll_bits & POLLIN)
+ /* An event has been signaled, inject an interrupt */
+ acrn_irqfd_inject(irqfd);
+
+ if (poll_bits & POLLHUP)
+ /* Do shutdown work in thread to hold wqh->lock */
+ queue_work(vm->irqfd_wq, &irqfd->shutdown);
+
+ 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;
+ struct fd f;
+ int ret = 0;
+
+ irqfd = kzalloc(sizeof(*irqfd), GFP_KERNEL);
+ 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);
+
+ f = fdget(args->fd);
+ if (!f.file) {
+ ret = -EBADF;
+ goto out;
+ }
+
+ eventfd = eventfd_ctx_fileget(f.file);
+ if (IS_ERR(eventfd)) {
+ ret = PTR_ERR(eventfd);
+ goto fail;
+ }
+
+ 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);
+
+ 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;
+ }
+ list_add_tail(&irqfd->list, &vm->irqfds);
+ mutex_unlock(&vm->irqfds_lock);
+
+ /* Check the pending event in this stage */
+ events = vfs_poll(f.file, &irqfd->pt);
+
+ if (events & EPOLLIN)
+ acrn_irqfd_inject(irqfd);
+
+ fdput(f);
+ return 0;
+fail:
+ if (eventfd && !IS_ERR(eventfd))
+ eventfd_ctx_put(eventfd);
+
+ fdput(f);
+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) {
+ hsm_irqfd_shutdown(irqfd);
+ break;
+ }
+ }
+ mutex_unlock(&vm->irqfds_lock);
+ eventfd_ctx_put(eventfd);
+
+ 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", 0, 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);
+ destroy_workqueue(vm->irqfd_wq);
+ mutex_lock(&vm->irqfds_lock);
+ list_for_each_entry_safe(irqfd, next, &vm->irqfds, list)
+ hsm_irqfd_shutdown(irqfd);
+ mutex_unlock(&vm->irqfds_lock);
+}
diff --git a/drivers/virt/acrn/mm.c b/drivers/virt/acrn/mm.c
new file mode 100644
index 000000000..b4ad8d452
--- /dev/null
+++ b/drivers/virt/acrn/mm.c
@@ -0,0 +1,329 @@
+// 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 "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(sizeof(*regions), GFP_KERNEL);
+ 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(sizeof(*region), GFP_KERNEL);
+ 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[%pK] service-GPA[%pK] 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(sizeof(*region), GFP_KERNEL);
+ 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[%pK] 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 = 0, 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;
+ unsigned long pfn;
+ struct vm_area_struct *vma;
+
+ if (!vm || !memmap)
+ return -EINVAL;
+
+ mmap_read_lock(current->mm);
+ vma = vma_lookup(current->mm, memmap->vma_base);
+ if (vma && ((vma->vm_flags & VM_PFNMAP) != 0)) {
+ if ((memmap->vma_base + memmap->len) > vma->vm_end) {
+ mmap_read_unlock(current->mm);
+ return -EINVAL;
+ }
+
+ ret = follow_pfn(vma, memmap->vma_base, &pfn);
+ mmap_read_unlock(current->mm);
+ if (ret < 0) {
+ dev_dbg(acrn_dev.this_device,
+ "Failed to lookup PFN at VMA:%pK.\n", (void *)memmap->vma_base);
+ return ret;
+ }
+
+ return acrn_mm_region_add(vm, memmap->user_vm_pa,
+ PFN_PHYS(pfn), memmap->len,
+ ACRN_MEM_TYPE_WB, memmap->attr);
+ }
+ mmap_read_unlock(current->mm);
+
+ /* Get the page number of the map region */
+ nr_pages = memmap->len >> PAGE_SHIFT;
+ 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 */
+ while (i < nr_pages) {
+ page = pages[i];
+ VM_BUG_ON_PAGE(PageTail(page), page);
+ order = compound_order(page);
+ nr_regions++;
+ i += 1 << order;
+ }
+
+ /* Prepare the vm_memory_region_batch */
+ regions_info = kzalloc(struct_size(regions_info, regions_op,
+ nr_regions), GFP_KERNEL);
+ if (!regions_info) {
+ ret = -ENOMEM;
+ goto unmap_kernel_map;
+ }
+
+ /* Fill each vm_memory_region_op */
+ vm_region = regions_info->regions_op;
+ regions_info->vmid = vm->vmid;
+ regions_info->regions_num = nr_regions;
+ regions_info->regions_gpa = virt_to_phys(vm_region);
+ user_vm_pa = memmap->user_vm_pa;
+ i = 0;
+ while (i < nr_pages) {
+ 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;
+ i += 1 << order;
+ }
+
+ /* 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[%pK] user-GPA[%pK] 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);
+}
diff --git a/drivers/virt/acrn/vm.c b/drivers/virt/acrn/vm.c
new file mode 100644
index 000000000..fbc9f1042
--- /dev/null
+++ b/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(sizeof(*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;
+}
diff --git a/drivers/virt/coco/efi_secret/Kconfig b/drivers/virt/coco/efi_secret/Kconfig
new file mode 100644
index 000000000..4404d198f
--- /dev/null
+++ b/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
+ 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.
diff --git a/drivers/virt/coco/efi_secret/Makefile b/drivers/virt/coco/efi_secret/Makefile
new file mode 100644
index 000000000..c7047ce80
--- /dev/null
+++ b/drivers/virt/coco/efi_secret/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_EFI_SECRET) += efi_secret.o
diff --git a/drivers/virt/coco/efi_secret/efi_secret.c b/drivers/virt/coco/efi_secret/efi_secret.c
new file mode 100644
index 000000000..e700a5ef7
--- /dev/null
+++ b/drivers/virt/coco/efi_secret/efi_secret.c
@@ -0,0 +1,349 @@
+// 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;
+ struct dentry *fs_dir;
+ struct dentry *fs_files[EFI_SECRET_NUM_FILES];
+ 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 efi_secret *s = efi_secret_get();
+ struct inode *inode = d_inode(dentry);
+ struct secret_entry *e = (struct secret_entry *)inode->i_private;
+ int i;
+
+ if (e) {
+ /* Zero out the secret data */
+ wipe_memory(e->data, secret_entry_data_len(e));
+ e->guid = NULL_GUID;
+ }
+
+ inode->i_private = NULL;
+
+ for (i = 0; i < EFI_SECRET_NUM_FILES; i++)
+ if (s->fs_files[i] == dentry)
+ s->fs_files[i] = NULL;
+
+ /*
+ * securityfs_remove tries to lock the directory's inode, but we reach
+ * the unlink callback when it's already locked
+ */
+ inode_unlock(dir);
+ securityfs_remove(dentry);
+ inode_lock(dir);
+
+ return 0;
+}
+
+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();
+ int i;
+
+ for (i = (EFI_SECRET_NUM_FILES - 1); i >= 0; i--) {
+ securityfs_remove(s->fs_files[i]);
+ s->fs_files[i] = NULL;
+ }
+
+ securityfs_remove(s->fs_dir);
+ s->fs_dir = NULL;
+
+ 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;
+ 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;
+ s->fs_dir = NULL;
+ memset(s->fs_files, 0, sizeof(s->fs_files));
+
+ 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;
+
+ dent = securityfs_create_dir("coco", s->secrets_dir);
+ if (IS_ERR(dent)) {
+ dev_err(&dev->dev, "Error creating coco securityfs directory entry err=%ld\n",
+ PTR_ERR(dent));
+ return PTR_ERR(dent);
+ }
+ d_inode(dent)->i_op = &efi_secret_dir_inode_operations;
+ s->fs_dir = dent;
+
+ 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, s->fs_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;
+ }
+
+ s->fs_files[i++] = dent;
+ }
+ 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 int efi_secret_remove(struct platform_device *dev)
+{
+ efi_secret_securityfs_teardown(dev);
+ efi_secret_unmap_area();
+ return 0;
+}
+
+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");
diff --git a/drivers/virt/coco/sev-guest/Kconfig b/drivers/virt/coco/sev-guest/Kconfig
new file mode 100644
index 000000000..da2d7ca53
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/Kconfig
@@ -0,0 +1,15 @@
+config SEV_GUEST
+ tristate "AMD SEV Guest driver"
+ default m
+ depends on AMD_MEM_ENCRYPT
+ select CRYPTO
+ select CRYPTO_AEAD2
+ select CRYPTO_GCM
+ 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.
diff --git a/drivers/virt/coco/sev-guest/Makefile b/drivers/virt/coco/sev-guest/Makefile
new file mode 100644
index 000000000..63d67c277
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_SEV_GUEST) += sev-guest.o
diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
new file mode 100644
index 000000000..c47e54b2a
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -0,0 +1,875 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Secure Encrypted Virtualization (SEV) guest driver interface
+ *
+ * Copyright (C) 2021 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 <crypto/aead.h>
+#include <linux/scatterlist.h>
+#include <linux/psp-sev.h>
+#include <uapi/linux/sev-guest.h>
+#include <uapi/linux/psp-sev.h>
+
+#include <asm/svm.h>
+#include <asm/sev.h>
+
+#include "sev-guest.h"
+
+#define DEVICE_NAME "sev-guest"
+#define AAD_LEN 48
+#define MSG_HDR_VER 1
+
+#define SNP_REQ_MAX_RETRY_DURATION (60*HZ)
+#define SNP_REQ_RETRY_DELAY (2*HZ)
+
+struct snp_guest_crypto {
+ struct crypto_aead *tfm;
+ u8 *iv, *authtag;
+ int iv_len, a_len;
+};
+
+struct snp_guest_dev {
+ struct device *dev;
+ struct miscdevice misc;
+
+ void *certs_data;
+ struct snp_guest_crypto *crypto;
+ /* request and response are in unencrypted memory */
+ struct snp_guest_msg *request, *response;
+
+ /*
+ * Avoid information leakage by double-buffering shared messages
+ * in fields that are in regular encrypted memory.
+ */
+ struct snp_guest_msg secret_request, secret_response;
+
+ struct snp_secrets_page_layout *layout;
+ struct snp_req_data input;
+ union {
+ struct snp_report_req report;
+ struct snp_derived_key_req derived_key;
+ struct snp_ext_report_req ext_report;
+ } req;
+ u32 *os_area_msg_seqno;
+ u8 *vmpck;
+};
+
+static u32 vmpck_id;
+module_param(vmpck_id, uint, 0444);
+MODULE_PARM_DESC(vmpck_id, "The VMPCK ID to use when communicating with the PSP.");
+
+/* Mutex to serialize the shared buffer access and command handling. */
+static DEFINE_MUTEX(snp_cmd_mutex);
+
+static bool is_vmpck_empty(struct snp_guest_dev *snp_dev)
+{
+ char zero_key[VMPCK_KEY_LEN] = {0};
+
+ if (snp_dev->vmpck)
+ return !memcmp(snp_dev->vmpck, zero_key, VMPCK_KEY_LEN);
+
+ return true;
+}
+
+/*
+ * If an error is received from the host or AMD Secure Processor (ASP) there
+ * are two options. Either retry the exact same encrypted request or discontinue
+ * using the VMPCK.
+ *
+ * This is because in the current encryption scheme GHCB v2 uses AES-GCM to
+ * encrypt the requests. The IV for this scheme is the sequence number. GCM
+ * cannot tolerate IV reuse.
+ *
+ * The ASP FW v1.51 only increments the sequence numbers on a successful
+ * guest<->ASP back and forth and only accepts messages at its exact sequence
+ * number.
+ *
+ * So if the sequence number were to be reused the encryption scheme is
+ * vulnerable. If the sequence number were incremented for a fresh IV the ASP
+ * will reject the request.
+ */
+static void snp_disable_vmpck(struct snp_guest_dev *snp_dev)
+{
+ dev_alert(snp_dev->dev, "Disabling vmpck_id %d to prevent IV reuse.\n",
+ vmpck_id);
+ memzero_explicit(snp_dev->vmpck, VMPCK_KEY_LEN);
+ snp_dev->vmpck = NULL;
+}
+
+static inline u64 __snp_get_msg_seqno(struct snp_guest_dev *snp_dev)
+{
+ u64 count;
+
+ lockdep_assert_held(&snp_cmd_mutex);
+
+ /* Read the current message sequence counter from secrets pages */
+ count = *snp_dev->os_area_msg_seqno;
+
+ return count + 1;
+}
+
+/* Return a non-zero on success */
+static u64 snp_get_msg_seqno(struct snp_guest_dev *snp_dev)
+{
+ u64 count = __snp_get_msg_seqno(snp_dev);
+
+ /*
+ * The message sequence counter for the SNP guest request is a 64-bit
+ * value but the version 2 of GHCB specification defines a 32-bit storage
+ * for it. If the counter exceeds the 32-bit value then return zero.
+ * The caller should check the return value, but if the caller happens to
+ * not check the value and use it, then the firmware treats zero as an
+ * invalid number and will fail the message request.
+ */
+ if (count >= UINT_MAX) {
+ dev_err(snp_dev->dev, "request message sequence counter overflow\n");
+ return 0;
+ }
+
+ return count;
+}
+
+static void snp_inc_msg_seqno(struct snp_guest_dev *snp_dev)
+{
+ /*
+ * The counter is also incremented by the PSP, so increment it by 2
+ * and save in secrets page.
+ */
+ *snp_dev->os_area_msg_seqno += 2;
+}
+
+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);
+}
+
+static struct snp_guest_crypto *init_crypto(struct snp_guest_dev *snp_dev, u8 *key, size_t keylen)
+{
+ struct snp_guest_crypto *crypto;
+
+ crypto = kzalloc(sizeof(*crypto), GFP_KERNEL_ACCOUNT);
+ if (!crypto)
+ return NULL;
+
+ crypto->tfm = crypto_alloc_aead("gcm(aes)", 0, 0);
+ if (IS_ERR(crypto->tfm))
+ goto e_free;
+
+ if (crypto_aead_setkey(crypto->tfm, key, keylen))
+ goto e_free_crypto;
+
+ crypto->iv_len = crypto_aead_ivsize(crypto->tfm);
+ crypto->iv = kmalloc(crypto->iv_len, GFP_KERNEL_ACCOUNT);
+ if (!crypto->iv)
+ goto e_free_crypto;
+
+ if (crypto_aead_authsize(crypto->tfm) > MAX_AUTHTAG_LEN) {
+ if (crypto_aead_setauthsize(crypto->tfm, MAX_AUTHTAG_LEN)) {
+ dev_err(snp_dev->dev, "failed to set authsize to %d\n", MAX_AUTHTAG_LEN);
+ goto e_free_iv;
+ }
+ }
+
+ crypto->a_len = crypto_aead_authsize(crypto->tfm);
+ crypto->authtag = kmalloc(crypto->a_len, GFP_KERNEL_ACCOUNT);
+ if (!crypto->authtag)
+ goto e_free_auth;
+
+ return crypto;
+
+e_free_auth:
+ kfree(crypto->authtag);
+e_free_iv:
+ kfree(crypto->iv);
+e_free_crypto:
+ crypto_free_aead(crypto->tfm);
+e_free:
+ kfree(crypto);
+
+ return NULL;
+}
+
+static void deinit_crypto(struct snp_guest_crypto *crypto)
+{
+ crypto_free_aead(crypto->tfm);
+ kfree(crypto->iv);
+ kfree(crypto->authtag);
+ kfree(crypto);
+}
+
+static int enc_dec_message(struct snp_guest_crypto *crypto, struct snp_guest_msg *msg,
+ u8 *src_buf, u8 *dst_buf, size_t len, bool enc)
+{
+ struct snp_guest_msg_hdr *hdr = &msg->hdr;
+ struct scatterlist src[3], dst[3];
+ DECLARE_CRYPTO_WAIT(wait);
+ struct aead_request *req;
+ int ret;
+
+ req = aead_request_alloc(crypto->tfm, GFP_KERNEL);
+ if (!req)
+ return -ENOMEM;
+
+ /*
+ * AEAD memory operations:
+ * +------ AAD -------+------- DATA -----+---- AUTHTAG----+
+ * | msg header | plaintext | hdr->authtag |
+ * | bytes 30h - 5Fh | or | |
+ * | | cipher | |
+ * +------------------+------------------+----------------+
+ */
+ sg_init_table(src, 3);
+ sg_set_buf(&src[0], &hdr->algo, AAD_LEN);
+ sg_set_buf(&src[1], src_buf, hdr->msg_sz);
+ sg_set_buf(&src[2], hdr->authtag, crypto->a_len);
+
+ sg_init_table(dst, 3);
+ sg_set_buf(&dst[0], &hdr->algo, AAD_LEN);
+ sg_set_buf(&dst[1], dst_buf, hdr->msg_sz);
+ sg_set_buf(&dst[2], hdr->authtag, crypto->a_len);
+
+ aead_request_set_ad(req, AAD_LEN);
+ aead_request_set_tfm(req, crypto->tfm);
+ aead_request_set_callback(req, 0, crypto_req_done, &wait);
+
+ aead_request_set_crypt(req, src, dst, len, crypto->iv);
+ ret = crypto_wait_req(enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req), &wait);
+
+ aead_request_free(req);
+ return ret;
+}
+
+static int __enc_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg,
+ void *plaintext, size_t len)
+{
+ struct snp_guest_crypto *crypto = snp_dev->crypto;
+ struct snp_guest_msg_hdr *hdr = &msg->hdr;
+
+ memset(crypto->iv, 0, crypto->iv_len);
+ memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno));
+
+ return enc_dec_message(crypto, msg, plaintext, msg->payload, len, true);
+}
+
+static int dec_payload(struct snp_guest_dev *snp_dev, struct snp_guest_msg *msg,
+ void *plaintext, size_t len)
+{
+ struct snp_guest_crypto *crypto = snp_dev->crypto;
+ struct snp_guest_msg_hdr *hdr = &msg->hdr;
+
+ /* Build IV with response buffer sequence number */
+ memset(crypto->iv, 0, crypto->iv_len);
+ memcpy(crypto->iv, &hdr->msg_seqno, sizeof(hdr->msg_seqno));
+
+ return enc_dec_message(crypto, msg, msg->payload, plaintext, len, false);
+}
+
+static int verify_and_dec_payload(struct snp_guest_dev *snp_dev, void *payload, u32 sz)
+{
+ struct snp_guest_crypto *crypto = snp_dev->crypto;
+ struct snp_guest_msg *resp = &snp_dev->secret_response;
+ struct snp_guest_msg *req = &snp_dev->secret_request;
+ struct snp_guest_msg_hdr *req_hdr = &req->hdr;
+ struct snp_guest_msg_hdr *resp_hdr = &resp->hdr;
+
+ dev_dbg(snp_dev->dev, "response [seqno %lld type %d version %d sz %d]\n",
+ resp_hdr->msg_seqno, resp_hdr->msg_type, resp_hdr->msg_version, resp_hdr->msg_sz);
+
+ /* Copy response from shared memory to encrypted memory. */
+ memcpy(resp, snp_dev->response, sizeof(*resp));
+
+ /* Verify that the sequence counter is incremented by 1 */
+ if (unlikely(resp_hdr->msg_seqno != (req_hdr->msg_seqno + 1)))
+ return -EBADMSG;
+
+ /* Verify response message type and version number. */
+ if (resp_hdr->msg_type != (req_hdr->msg_type + 1) ||
+ resp_hdr->msg_version != req_hdr->msg_version)
+ return -EBADMSG;
+
+ /*
+ * If the message size is greater than our buffer length then return
+ * an error.
+ */
+ if (unlikely((resp_hdr->msg_sz + crypto->a_len) > sz))
+ return -EBADMSG;
+
+ /* Decrypt the payload */
+ return dec_payload(snp_dev, resp, payload, resp_hdr->msg_sz + crypto->a_len);
+}
+
+static int enc_payload(struct snp_guest_dev *snp_dev, u64 seqno, int version, u8 type,
+ void *payload, size_t sz)
+{
+ struct snp_guest_msg *req = &snp_dev->secret_request;
+ struct snp_guest_msg_hdr *hdr = &req->hdr;
+
+ memset(req, 0, sizeof(*req));
+
+ hdr->algo = SNP_AEAD_AES_256_GCM;
+ hdr->hdr_version = MSG_HDR_VER;
+ hdr->hdr_sz = sizeof(*hdr);
+ hdr->msg_type = type;
+ hdr->msg_version = version;
+ hdr->msg_seqno = seqno;
+ hdr->msg_vmpck = vmpck_id;
+ hdr->msg_sz = sz;
+
+ /* Verify the sequence number is non-zero */
+ if (!hdr->msg_seqno)
+ return -ENOSR;
+
+ dev_dbg(snp_dev->dev, "request [seqno %lld type %d version %d sz %d]\n",
+ hdr->msg_seqno, hdr->msg_type, hdr->msg_version, hdr->msg_sz);
+
+ return __enc_payload(snp_dev, req, payload, sz);
+}
+
+static int __handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code,
+ struct snp_guest_request_ioctl *rio)
+{
+ unsigned long req_start = jiffies;
+ unsigned int override_npages = 0;
+ u64 override_err = 0;
+ int rc;
+
+retry_request:
+ /*
+ * Call firmware to process the request. In this function the encrypted
+ * message enters shared memory with the host. So after this call the
+ * sequence number must be incremented or the VMPCK must be deleted to
+ * prevent reuse of the IV.
+ */
+ rc = snp_issue_guest_request(exit_code, &snp_dev->input, rio);
+ switch (rc) {
+ case -ENOSPC:
+ /*
+ * If the extended guest request fails due to having too
+ * small of a certificate data buffer, retry the same
+ * guest request without the extended data request in
+ * order to increment the sequence number and thus avoid
+ * IV reuse.
+ */
+ override_npages = snp_dev->input.data_npages;
+ exit_code = SVM_VMGEXIT_GUEST_REQUEST;
+
+ /*
+ * Override the error to inform callers the given extended
+ * request buffer size was too small and give the caller the
+ * required buffer size.
+ */
+ override_err = SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN);
+
+ /*
+ * If this call to the firmware succeeds, the sequence number can
+ * be incremented allowing for continued use of the VMPCK. If
+ * there is an error reflected in the return value, this value
+ * is checked further down and the result will be the deletion
+ * of the VMPCK and the error code being propagated back to the
+ * user as an ioctl() return code.
+ */
+ goto retry_request;
+
+ /*
+ * The host may return SNP_GUEST_VMM_ERR_BUSY if the request has been
+ * throttled. Retry in the driver to avoid returning and reusing the
+ * message sequence number on a different message.
+ */
+ case -EAGAIN:
+ if (jiffies - req_start > SNP_REQ_MAX_RETRY_DURATION) {
+ rc = -ETIMEDOUT;
+ break;
+ }
+ schedule_timeout_killable(SNP_REQ_RETRY_DELAY);
+ goto retry_request;
+ }
+
+ /*
+ * Increment the message sequence number. There is no harm in doing
+ * this now because decryption uses the value stored in the response
+ * structure and any failure will wipe the VMPCK, preventing further
+ * use anyway.
+ */
+ snp_inc_msg_seqno(snp_dev);
+
+ if (override_err) {
+ rio->exitinfo2 = override_err;
+
+ /*
+ * If an extended guest request was issued and the supplied certificate
+ * buffer was not large enough, a standard guest request was issued to
+ * prevent IV reuse. If the standard request was successful, return -EIO
+ * back to the caller as would have originally been returned.
+ */
+ if (!rc && override_err == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN))
+ rc = -EIO;
+ }
+
+ if (override_npages)
+ snp_dev->input.data_npages = override_npages;
+
+ return rc;
+}
+
+static int handle_guest_request(struct snp_guest_dev *snp_dev, u64 exit_code,
+ struct snp_guest_request_ioctl *rio, u8 type,
+ void *req_buf, size_t req_sz, void *resp_buf,
+ u32 resp_sz)
+{
+ u64 seqno;
+ int rc;
+
+ /* Get message sequence and verify that its a non-zero */
+ seqno = snp_get_msg_seqno(snp_dev);
+ if (!seqno)
+ return -EIO;
+
+ /* Clear shared memory's response for the host to populate. */
+ memset(snp_dev->response, 0, sizeof(struct snp_guest_msg));
+
+ /* Encrypt the userspace provided payload in snp_dev->secret_request. */
+ rc = enc_payload(snp_dev, seqno, rio->msg_version, type, req_buf, req_sz);
+ if (rc)
+ return rc;
+
+ /*
+ * Write the fully encrypted request to the shared unencrypted
+ * request page.
+ */
+ memcpy(snp_dev->request, &snp_dev->secret_request,
+ sizeof(snp_dev->secret_request));
+
+ rc = __handle_guest_request(snp_dev, exit_code, rio);
+ if (rc) {
+ if (rc == -EIO &&
+ rio->exitinfo2 == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN))
+ return rc;
+
+ dev_alert(snp_dev->dev,
+ "Detected error from ASP request. rc: %d, exitinfo2: 0x%llx\n",
+ rc, rio->exitinfo2);
+
+ snp_disable_vmpck(snp_dev);
+ return rc;
+ }
+
+ rc = verify_and_dec_payload(snp_dev, resp_buf, resp_sz);
+ if (rc) {
+ dev_alert(snp_dev->dev, "Detected unexpected decode failure from ASP. rc: %d\n", rc);
+ snp_disable_vmpck(snp_dev);
+ return rc;
+ }
+
+ return 0;
+}
+
+static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
+{
+ struct snp_guest_crypto *crypto = snp_dev->crypto;
+ struct snp_report_req *req = &snp_dev->req.report;
+ struct snp_report_resp *resp;
+ int rc, resp_len;
+
+ lockdep_assert_held(&snp_cmd_mutex);
+
+ if (!arg->req_data || !arg->resp_data)
+ return -EINVAL;
+
+ if (copy_from_user(req, (void __user *)arg->req_data, sizeof(*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(resp->data) + crypto->a_len;
+ resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT);
+ if (!resp)
+ return -ENOMEM;
+
+ rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg,
+ SNP_MSG_REPORT_REQ, req, sizeof(*req), resp->data,
+ resp_len);
+ if (rc)
+ goto e_free;
+
+ if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp)))
+ rc = -EFAULT;
+
+e_free:
+ kfree(resp);
+ return rc;
+}
+
+static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
+{
+ struct snp_derived_key_req *req = &snp_dev->req.derived_key;
+ struct snp_guest_crypto *crypto = snp_dev->crypto;
+ struct snp_derived_key_resp resp = {0};
+ int rc, resp_len;
+ /* Response data is 64 bytes and max authsize for GCM is 16 bytes. */
+ u8 buf[64 + 16];
+
+ lockdep_assert_held(&snp_cmd_mutex);
+
+ 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(resp.data) + crypto->a_len;
+ if (sizeof(buf) < resp_len)
+ return -ENOMEM;
+
+ if (copy_from_user(req, (void __user *)arg->req_data, sizeof(*req)))
+ return -EFAULT;
+
+ rc = handle_guest_request(snp_dev, SVM_VMGEXIT_GUEST_REQUEST, arg,
+ SNP_MSG_KEY_REQ, req, sizeof(*req), buf, resp_len);
+ if (rc)
+ return rc;
+
+ memcpy(resp.data, buf, sizeof(resp.data));
+ if (copy_to_user((void __user *)arg->resp_data, &resp, sizeof(resp)))
+ rc = -EFAULT;
+
+ /* The response buffer contains the sensitive data, explicitly clear it. */
+ memzero_explicit(buf, sizeof(buf));
+ memzero_explicit(&resp, sizeof(resp));
+ return rc;
+}
+
+static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
+{
+ struct snp_ext_report_req *req = &snp_dev->req.ext_report;
+ struct snp_guest_crypto *crypto = snp_dev->crypto;
+ struct snp_report_resp *resp;
+ int ret, npages = 0, resp_len;
+
+ lockdep_assert_held(&snp_cmd_mutex);
+
+ if (!arg->req_data || !arg->resp_data)
+ return -EINVAL;
+
+ if (copy_from_user(req, (void __user *)arg->req_data, sizeof(*req)))
+ return -EFAULT;
+
+ /* userspace does not want certificate data */
+ if (!req->certs_len || !req->certs_address)
+ goto cmd;
+
+ if (req->certs_len > SEV_FW_BLOB_MAX_SIZE ||
+ !IS_ALIGNED(req->certs_len, PAGE_SIZE))
+ return -EINVAL;
+
+ if (!access_ok((const void __user *)req->certs_address, 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.
+ */
+ memset(snp_dev->certs_data, 0, req->certs_len);
+ npages = req->certs_len >> PAGE_SHIFT;
+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(resp->data) + crypto->a_len;
+ resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT);
+ if (!resp)
+ return -ENOMEM;
+
+ snp_dev->input.data_npages = npages;
+ ret = handle_guest_request(snp_dev, SVM_VMGEXIT_EXT_GUEST_REQUEST, arg,
+ SNP_MSG_REPORT_REQ, &req->data,
+ sizeof(req->data), resp->data, resp_len);
+
+ /* If certs length is invalid then copy the returned length */
+ if (arg->vmm_error == SNP_GUEST_VMM_ERR_INVALID_LEN) {
+ req->certs_len = snp_dev->input.data_npages << PAGE_SHIFT;
+
+ if (copy_to_user((void __user *)arg->req_data, req, sizeof(*req)))
+ ret = -EFAULT;
+ }
+
+ if (ret)
+ goto e_free;
+
+ if (npages &&
+ copy_to_user((void __user *)req->certs_address, snp_dev->certs_data,
+ req->certs_len)) {
+ ret = -EFAULT;
+ goto e_free;
+ }
+
+ if (copy_to_user((void __user *)arg->resp_data, resp, sizeof(*resp)))
+ ret = -EFAULT;
+
+e_free:
+ kfree(resp);
+ 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;
+ 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;
+
+ mutex_lock(&snp_cmd_mutex);
+
+ /* Check if the VMPCK is not empty */
+ if (is_vmpck_empty(snp_dev)) {
+ dev_err_ratelimited(snp_dev->dev, "VMPCK is disabled\n");
+ mutex_unlock(&snp_cmd_mutex);
+ return -ENOTTY;
+ }
+
+ 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:
+ ret = get_ext_report(snp_dev, &input);
+ break;
+ default:
+ break;
+ }
+
+ mutex_unlock(&snp_cmd_mutex);
+
+ if (input.exitinfo2 && copy_to_user(argp, &input, sizeof(input)))
+ return -EFAULT;
+
+ return ret;
+}
+
+static void free_shared_pages(void *buf, size_t sz)
+{
+ unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
+ int ret;
+
+ if (!buf)
+ return;
+
+ ret = set_memory_encrypted((unsigned long)buf, npages);
+ if (ret) {
+ WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n");
+ return;
+ }
+
+ __free_pages(virt_to_page(buf), get_order(sz));
+}
+
+static void *alloc_shared_pages(struct device *dev, size_t sz)
+{
+ unsigned int npages = PAGE_ALIGN(sz) >> PAGE_SHIFT;
+ struct page *page;
+ int ret;
+
+ page = alloc_pages(GFP_KERNEL_ACCOUNT, get_order(sz));
+ if (!page)
+ return NULL;
+
+ ret = set_memory_decrypted((unsigned long)page_address(page), npages);
+ if (ret) {
+ dev_err(dev, "failed to mark page shared, ret=%d\n", ret);
+ __free_pages(page, get_order(sz));
+ return NULL;
+ }
+
+ return page_address(page);
+}
+
+static const struct file_operations snp_guest_fops = {
+ .owner = THIS_MODULE,
+ .unlocked_ioctl = snp_guest_ioctl,
+};
+
+static u8 *get_vmpck(int id, struct snp_secrets_page_layout *layout, u32 **seqno)
+{
+ u8 *key = NULL;
+
+ switch (id) {
+ case 0:
+ *seqno = &layout->os_area.msg_seqno_0;
+ key = layout->vmpck0;
+ break;
+ case 1:
+ *seqno = &layout->os_area.msg_seqno_1;
+ key = layout->vmpck1;
+ break;
+ case 2:
+ *seqno = &layout->os_area.msg_seqno_2;
+ key = layout->vmpck2;
+ break;
+ case 3:
+ *seqno = &layout->os_area.msg_seqno_3;
+ key = layout->vmpck3;
+ break;
+ default:
+ break;
+ }
+
+ return key;
+}
+
+static int __init sev_guest_probe(struct platform_device *pdev)
+{
+ struct snp_secrets_page_layout *layout;
+ struct sev_guest_platform_data *data;
+ struct device *dev = &pdev->dev;
+ struct snp_guest_dev *snp_dev;
+ struct miscdevice *misc;
+ void __iomem *mapping;
+ int ret;
+
+ if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return -ENODEV;
+
+ if (!dev->platform_data)
+ return -ENODEV;
+
+ data = (struct sev_guest_platform_data *)dev->platform_data;
+ mapping = ioremap_encrypted(data->secrets_gpa, PAGE_SIZE);
+ if (!mapping)
+ return -ENODEV;
+
+ layout = (__force void *)mapping;
+
+ ret = -ENOMEM;
+ snp_dev = devm_kzalloc(&pdev->dev, sizeof(struct snp_guest_dev), GFP_KERNEL);
+ if (!snp_dev)
+ goto e_unmap;
+
+ ret = -EINVAL;
+ snp_dev->vmpck = get_vmpck(vmpck_id, layout, &snp_dev->os_area_msg_seqno);
+ if (!snp_dev->vmpck) {
+ dev_err(dev, "invalid vmpck id %d\n", vmpck_id);
+ goto e_unmap;
+ }
+
+ /* Verify that VMPCK is not zero. */
+ if (is_vmpck_empty(snp_dev)) {
+ dev_err(dev, "vmpck id %d is null\n", vmpck_id);
+ goto e_unmap;
+ }
+
+ platform_set_drvdata(pdev, snp_dev);
+ snp_dev->dev = dev;
+ snp_dev->layout = layout;
+
+ /* Allocate the shared page used for the request and response message. */
+ snp_dev->request = alloc_shared_pages(dev, sizeof(struct snp_guest_msg));
+ if (!snp_dev->request)
+ goto e_unmap;
+
+ snp_dev->response = alloc_shared_pages(dev, sizeof(struct snp_guest_msg));
+ if (!snp_dev->response)
+ goto e_free_request;
+
+ snp_dev->certs_data = alloc_shared_pages(dev, SEV_FW_BLOB_MAX_SIZE);
+ if (!snp_dev->certs_data)
+ goto e_free_response;
+
+ ret = -EIO;
+ snp_dev->crypto = init_crypto(snp_dev, snp_dev->vmpck, VMPCK_KEY_LEN);
+ if (!snp_dev->crypto)
+ goto e_free_cert_data;
+
+ misc = &snp_dev->misc;
+ misc->minor = MISC_DYNAMIC_MINOR;
+ misc->name = DEVICE_NAME;
+ misc->fops = &snp_guest_fops;
+
+ /* initial the input address for guest request */
+ snp_dev->input.req_gpa = __pa(snp_dev->request);
+ snp_dev->input.resp_gpa = __pa(snp_dev->response);
+ snp_dev->input.data_gpa = __pa(snp_dev->certs_data);
+
+ ret = misc_register(misc);
+ if (ret)
+ goto e_free_cert_data;
+
+ dev_info(dev, "Initialized SEV guest driver (using vmpck_id %d)\n", vmpck_id);
+ return 0;
+
+e_free_cert_data:
+ free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE);
+e_free_response:
+ free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg));
+e_free_request:
+ free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg));
+e_unmap:
+ iounmap(mapping);
+ return ret;
+}
+
+static int __exit sev_guest_remove(struct platform_device *pdev)
+{
+ struct snp_guest_dev *snp_dev = platform_get_drvdata(pdev);
+
+ free_shared_pages(snp_dev->certs_data, SEV_FW_BLOB_MAX_SIZE);
+ free_shared_pages(snp_dev->response, sizeof(struct snp_guest_msg));
+ free_shared_pages(snp_dev->request, sizeof(struct snp_guest_msg));
+ deinit_crypto(snp_dev->crypto);
+ misc_deregister(&snp_dev->misc);
+
+ return 0;
+}
+
+/*
+ * 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".
+ */
+static struct platform_driver sev_guest_driver = {
+ .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");
diff --git a/drivers/virt/coco/sev-guest/sev-guest.h b/drivers/virt/coco/sev-guest/sev-guest.h
new file mode 100644
index 000000000..21bda26fd
--- /dev/null
+++ b/drivers/virt/coco/sev-guest/sev-guest.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Advanced Micro Devices, Inc.
+ *
+ * Author: Brijesh Singh <brijesh.singh@amd.com>
+ *
+ * SEV-SNP API spec is available at https://developer.amd.com/sev
+ */
+
+#ifndef __VIRT_SEVGUEST_H__
+#define __VIRT_SEVGUEST_H__
+
+#include <linux/types.h>
+
+#define MAX_AUTHTAG_LEN 32
+
+/* See SNP spec SNP_GUEST_REQUEST section for the structure */
+enum msg_type {
+ SNP_MSG_TYPE_INVALID = 0,
+ SNP_MSG_CPUID_REQ,
+ SNP_MSG_CPUID_RSP,
+ SNP_MSG_KEY_REQ,
+ SNP_MSG_KEY_RSP,
+ SNP_MSG_REPORT_REQ,
+ SNP_MSG_REPORT_RSP,
+ SNP_MSG_EXPORT_REQ,
+ SNP_MSG_EXPORT_RSP,
+ SNP_MSG_IMPORT_REQ,
+ SNP_MSG_IMPORT_RSP,
+ SNP_MSG_ABSORB_REQ,
+ SNP_MSG_ABSORB_RSP,
+ SNP_MSG_VMRK_REQ,
+ SNP_MSG_VMRK_RSP,
+
+ SNP_MSG_TYPE_MAX
+};
+
+enum aead_algo {
+ SNP_AEAD_INVALID,
+ SNP_AEAD_AES_256_GCM,
+};
+
+struct snp_guest_msg_hdr {
+ u8 authtag[MAX_AUTHTAG_LEN];
+ u64 msg_seqno;
+ u8 rsvd1[8];
+ u8 algo;
+ u8 hdr_version;
+ u16 hdr_sz;
+ u8 msg_type;
+ u8 msg_version;
+ u16 msg_sz;
+ u32 rsvd2;
+ u8 msg_vmpck;
+ u8 rsvd3[35];
+} __packed;
+
+struct snp_guest_msg {
+ struct snp_guest_msg_hdr hdr;
+ u8 payload[4000];
+} __packed;
+
+#endif /* __VIRT_SEVGUEST_H__ */
diff --git a/drivers/virt/fsl_hypervisor.c b/drivers/virt/fsl_hypervisor.c
new file mode 100644
index 000000000..07035249a
--- /dev/null
+++ b/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 = kcalloc(num_pages, sizeof(struct page *), GFP_KERNEL);
+ 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(sizeof(struct doorbell_queue), GFP_KERNEL);
+ 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_find_property(node, "fsl,hv-version", NULL) != NULL;
+
+ 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 == NO_IRQ)) {
+ pr_err("fsl-hv: no 'interrupts' property in %pOF node\n",
+ np);
+ continue;
+ }
+
+ dbisr = kzalloc(sizeof(*dbisr), GFP_KERNEL);
+ 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");
diff --git a/drivers/virt/nitro_enclaves/Kconfig b/drivers/virt/nitro_enclaves/Kconfig
new file mode 100644
index 000000000..dc4d25c26
--- /dev/null
+++ b/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.
diff --git a/drivers/virt/nitro_enclaves/Makefile b/drivers/virt/nitro_enclaves/Makefile
new file mode 100644
index 000000000..da61260f2
--- /dev/null
+++ b/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
diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.c b/drivers/virt/nitro_enclaves/ne_misc_dev.c
new file mode 100644
index 000000000..241b94f62
--- /dev/null
+++ b/drivers/virt/nitro_enclaves/ne_misc_dev.c
@@ -0,0 +1,1783 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2020-2021 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ */
+
+/**
+ * DOC: Enclave lifetime management driver for Nitro Enclaves (NE).
+ * Nitro is a hypervisor that has been developed by Amazon.
+ */
+
+#include <linux/anon_inodes.h>
+#include <linux/capability.h>
+#include <linux/cpu.h>
+#include <linux/device.h>
+#include <linux/file.h>
+#include <linux/hugetlb.h>
+#include <linux/limits.h>
+#include <linux/list.h>
+#include <linux/miscdevice.h>
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/nitro_enclaves.h>
+#include <linux/pci.h>
+#include <linux/poll.h>
+#include <linux/range.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <uapi/linux/vm_sockets.h>
+
+#include "ne_misc_dev.h"
+#include "ne_pci_dev.h"
+
+/**
+ * NE_CPUS_SIZE - Size for max 128 CPUs, for now, in a cpu-list string, comma
+ * separated. The NE CPU pool includes CPUs from a single NUMA
+ * node.
+ */
+#define NE_CPUS_SIZE (512)
+
+/**
+ * NE_EIF_LOAD_OFFSET - The offset where to copy the Enclave Image Format (EIF)
+ * image in enclave memory.
+ */
+#define NE_EIF_LOAD_OFFSET (8 * 1024UL * 1024UL)
+
+/**
+ * NE_MIN_ENCLAVE_MEM_SIZE - The minimum memory size an enclave can be launched
+ * with.
+ */
+#define NE_MIN_ENCLAVE_MEM_SIZE (64 * 1024UL * 1024UL)
+
+/**
+ * NE_MIN_MEM_REGION_SIZE - The minimum size of an enclave memory region.
+ */
+#define NE_MIN_MEM_REGION_SIZE (2 * 1024UL * 1024UL)
+
+/**
+ * NE_PARENT_VM_CID - The CID for the vsock device of the primary / parent VM.
+ */
+#define NE_PARENT_VM_CID (3)
+
+static long ne_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+
+static const struct file_operations ne_fops = {
+ .owner = THIS_MODULE,
+ .llseek = noop_llseek,
+ .unlocked_ioctl = ne_ioctl,
+};
+
+static struct miscdevice ne_misc_dev = {
+ .minor = MISC_DYNAMIC_MINOR,
+ .name = "nitro_enclaves",
+ .fops = &ne_fops,
+ .mode = 0660,
+};
+
+struct ne_devs ne_devs = {
+ .ne_misc_dev = &ne_misc_dev,
+};
+
+/*
+ * TODO: Update logic to create new sysfs entries instead of using
+ * a kernel parameter e.g. if multiple sysfs files needed.
+ */
+static int ne_set_kernel_param(const char *val, const struct kernel_param *kp);
+
+static const struct kernel_param_ops ne_cpu_pool_ops = {
+ .get = param_get_string,
+ .set = ne_set_kernel_param,
+};
+
+static char ne_cpus[NE_CPUS_SIZE];
+static struct kparam_string ne_cpus_arg = {
+ .maxlen = sizeof(ne_cpus),
+ .string = ne_cpus,
+};
+
+module_param_cb(ne_cpus, &ne_cpu_pool_ops, &ne_cpus_arg, 0644);
+/* https://www.kernel.org/doc/html/latest/admin-guide/kernel-parameters.html#cpu-lists */
+MODULE_PARM_DESC(ne_cpus, "<cpu-list> - CPU pool used for Nitro Enclaves");
+
+/**
+ * struct ne_cpu_pool - CPU pool used for Nitro Enclaves.
+ * @avail_threads_per_core: Available full CPU cores to be dedicated to
+ * enclave(s). The cpumasks from the array, indexed
+ * by core id, contain all the threads from the
+ * available cores, that are not set for created
+ * enclave(s). The full CPU cores are part of the
+ * NE CPU pool.
+ * @mutex: Mutex for the access to the NE CPU pool.
+ * @nr_parent_vm_cores : The size of the available threads per core array.
+ * The total number of CPU cores available on the
+ * primary / parent VM.
+ * @nr_threads_per_core: The number of threads that a full CPU core has.
+ * @numa_node: NUMA node of the CPUs in the pool.
+ */
+struct ne_cpu_pool {
+ cpumask_var_t *avail_threads_per_core;
+ struct mutex mutex;
+ unsigned int nr_parent_vm_cores;
+ unsigned int nr_threads_per_core;
+ int numa_node;
+};
+
+static struct ne_cpu_pool ne_cpu_pool;
+
+/**
+ * struct ne_phys_contig_mem_regions - Contiguous physical memory regions.
+ * @num: The number of regions that currently has.
+ * @regions: The array of physical memory regions.
+ */
+struct ne_phys_contig_mem_regions {
+ unsigned long num;
+ struct range *regions;
+};
+
+/**
+ * ne_check_enclaves_created() - Verify if at least one enclave has been created.
+ * @void: No parameters provided.
+ *
+ * Context: Process context.
+ * Return:
+ * * True if at least one enclave is created.
+ * * False otherwise.
+ */
+static bool ne_check_enclaves_created(void)
+{
+ struct ne_pci_dev *ne_pci_dev = ne_devs.ne_pci_dev;
+ bool ret = false;
+
+ if (!ne_pci_dev)
+ return ret;
+
+ mutex_lock(&ne_pci_dev->enclaves_list_mutex);
+
+ if (!list_empty(&ne_pci_dev->enclaves_list))
+ ret = true;
+
+ mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+
+ return ret;
+}
+
+/**
+ * ne_setup_cpu_pool() - Set the NE CPU pool after handling sanity checks such
+ * as not sharing CPU cores with the primary / parent VM
+ * or not using CPU 0, which should remain available for
+ * the primary / parent VM. Offline the CPUs from the
+ * pool after the checks passed.
+ * @ne_cpu_list: The CPU list used for setting NE CPU pool.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_setup_cpu_pool(const char *ne_cpu_list)
+{
+ int core_id = -1;
+ unsigned int cpu = 0;
+ cpumask_var_t cpu_pool;
+ unsigned int cpu_sibling = 0;
+ unsigned int i = 0;
+ int numa_node = -1;
+ int rc = -EINVAL;
+
+ if (!zalloc_cpumask_var(&cpu_pool, GFP_KERNEL))
+ return -ENOMEM;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ rc = cpulist_parse(ne_cpu_list, cpu_pool);
+ if (rc < 0) {
+ pr_err("%s: Error in cpulist parse [rc=%d]\n", ne_misc_dev.name, rc);
+
+ goto free_pool_cpumask;
+ }
+
+ cpu = cpumask_any(cpu_pool);
+ if (cpu >= nr_cpu_ids) {
+ pr_err("%s: No CPUs available in CPU pool\n", ne_misc_dev.name);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+
+ /*
+ * Check if the CPUs are online, to further get info about them
+ * e.g. numa node, core id, siblings.
+ */
+ for_each_cpu(cpu, cpu_pool)
+ if (cpu_is_offline(cpu)) {
+ pr_err("%s: CPU %d is offline, has to be online to get its metadata\n",
+ ne_misc_dev.name, cpu);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+
+ /*
+ * Check if the CPUs from the NE CPU pool are from the same NUMA node.
+ */
+ for_each_cpu(cpu, cpu_pool)
+ if (numa_node < 0) {
+ numa_node = cpu_to_node(cpu);
+ if (numa_node < 0) {
+ pr_err("%s: Invalid NUMA node %d\n",
+ ne_misc_dev.name, numa_node);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+ } else {
+ if (numa_node != cpu_to_node(cpu)) {
+ pr_err("%s: CPUs with different NUMA nodes\n",
+ ne_misc_dev.name);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+ }
+
+ /*
+ * Check if CPU 0 and its siblings are included in the provided CPU pool
+ * They should remain available for the primary / parent VM.
+ */
+ if (cpumask_test_cpu(0, cpu_pool)) {
+ pr_err("%s: CPU 0 has to remain available\n", ne_misc_dev.name);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+
+ for_each_cpu(cpu_sibling, topology_sibling_cpumask(0)) {
+ if (cpumask_test_cpu(cpu_sibling, cpu_pool)) {
+ pr_err("%s: CPU sibling %d for CPU 0 is in CPU pool\n",
+ ne_misc_dev.name, cpu_sibling);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+ }
+
+ /*
+ * Check if CPU siblings are included in the provided CPU pool. The
+ * expectation is that full CPU cores are made available in the CPU pool
+ * for enclaves.
+ */
+ for_each_cpu(cpu, cpu_pool) {
+ for_each_cpu(cpu_sibling, topology_sibling_cpumask(cpu)) {
+ if (!cpumask_test_cpu(cpu_sibling, cpu_pool)) {
+ pr_err("%s: CPU %d is not in CPU pool\n",
+ ne_misc_dev.name, cpu_sibling);
+
+ rc = -EINVAL;
+
+ goto free_pool_cpumask;
+ }
+ }
+ }
+
+ /* Calculate the number of threads from a full CPU core. */
+ cpu = cpumask_any(cpu_pool);
+ for_each_cpu(cpu_sibling, topology_sibling_cpumask(cpu))
+ ne_cpu_pool.nr_threads_per_core++;
+
+ ne_cpu_pool.nr_parent_vm_cores = nr_cpu_ids / ne_cpu_pool.nr_threads_per_core;
+
+ ne_cpu_pool.avail_threads_per_core = kcalloc(ne_cpu_pool.nr_parent_vm_cores,
+ sizeof(*ne_cpu_pool.avail_threads_per_core),
+ GFP_KERNEL);
+ if (!ne_cpu_pool.avail_threads_per_core) {
+ rc = -ENOMEM;
+
+ goto free_pool_cpumask;
+ }
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ if (!zalloc_cpumask_var(&ne_cpu_pool.avail_threads_per_core[i], GFP_KERNEL)) {
+ rc = -ENOMEM;
+
+ goto free_cores_cpumask;
+ }
+
+ /*
+ * Split the NE CPU pool in threads per core to keep the CPU topology
+ * after offlining the CPUs.
+ */
+ for_each_cpu(cpu, cpu_pool) {
+ core_id = topology_core_id(cpu);
+ if (core_id < 0 || core_id >= ne_cpu_pool.nr_parent_vm_cores) {
+ pr_err("%s: Invalid core id %d for CPU %d\n",
+ ne_misc_dev.name, core_id, cpu);
+
+ rc = -EINVAL;
+
+ goto clear_cpumask;
+ }
+
+ cpumask_set_cpu(cpu, ne_cpu_pool.avail_threads_per_core[core_id]);
+ }
+
+ /*
+ * CPUs that are given to enclave(s) should not be considered online
+ * by Linux anymore, as the hypervisor will degrade them to floating.
+ * The physical CPUs (full cores) are carved out of the primary / parent
+ * VM and given to the enclave VM. The same number of vCPUs would run
+ * on less pCPUs for the primary / parent VM.
+ *
+ * We offline them here, to not degrade performance and expose correct
+ * topology to Linux and user space.
+ */
+ for_each_cpu(cpu, cpu_pool) {
+ rc = remove_cpu(cpu);
+ if (rc != 0) {
+ pr_err("%s: CPU %d is not offlined [rc=%d]\n",
+ ne_misc_dev.name, cpu, rc);
+
+ goto online_cpus;
+ }
+ }
+
+ free_cpumask_var(cpu_pool);
+
+ ne_cpu_pool.numa_node = numa_node;
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return 0;
+
+online_cpus:
+ for_each_cpu(cpu, cpu_pool)
+ add_cpu(cpu);
+clear_cpumask:
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ cpumask_clear(ne_cpu_pool.avail_threads_per_core[i]);
+free_cores_cpumask:
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ free_cpumask_var(ne_cpu_pool.avail_threads_per_core[i]);
+ kfree(ne_cpu_pool.avail_threads_per_core);
+free_pool_cpumask:
+ free_cpumask_var(cpu_pool);
+ ne_cpu_pool.nr_parent_vm_cores = 0;
+ ne_cpu_pool.nr_threads_per_core = 0;
+ ne_cpu_pool.numa_node = -1;
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return rc;
+}
+
+/**
+ * ne_teardown_cpu_pool() - Online the CPUs from the NE CPU pool and cleanup the
+ * CPU pool.
+ * @void: No parameters provided.
+ *
+ * Context: Process context.
+ */
+static void ne_teardown_cpu_pool(void)
+{
+ unsigned int cpu = 0;
+ unsigned int i = 0;
+ int rc = -EINVAL;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ if (!ne_cpu_pool.nr_parent_vm_cores) {
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return;
+ }
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++) {
+ for_each_cpu(cpu, ne_cpu_pool.avail_threads_per_core[i]) {
+ rc = add_cpu(cpu);
+ if (rc != 0)
+ pr_err("%s: CPU %d is not onlined [rc=%d]\n",
+ ne_misc_dev.name, cpu, rc);
+ }
+
+ cpumask_clear(ne_cpu_pool.avail_threads_per_core[i]);
+
+ free_cpumask_var(ne_cpu_pool.avail_threads_per_core[i]);
+ }
+
+ kfree(ne_cpu_pool.avail_threads_per_core);
+ ne_cpu_pool.nr_parent_vm_cores = 0;
+ ne_cpu_pool.nr_threads_per_core = 0;
+ ne_cpu_pool.numa_node = -1;
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+}
+
+/**
+ * ne_set_kernel_param() - Set the NE CPU pool value via the NE kernel parameter.
+ * @val: NE CPU pool string value.
+ * @kp : NE kernel parameter associated with the NE CPU pool.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_set_kernel_param(const char *val, const struct kernel_param *kp)
+{
+ char error_val[] = "";
+ int rc = -EINVAL;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (ne_check_enclaves_created()) {
+ pr_err("%s: The CPU pool is used by enclave(s)\n", ne_misc_dev.name);
+
+ return -EPERM;
+ }
+
+ ne_teardown_cpu_pool();
+
+ rc = ne_setup_cpu_pool(val);
+ if (rc < 0) {
+ pr_err("%s: Error in setup CPU pool [rc=%d]\n", ne_misc_dev.name, rc);
+
+ param_set_copystring(error_val, kp);
+
+ return rc;
+ }
+
+ rc = param_set_copystring(val, kp);
+ if (rc < 0) {
+ pr_err("%s: Error in param set copystring [rc=%d]\n", ne_misc_dev.name, rc);
+
+ ne_teardown_cpu_pool();
+
+ param_set_copystring(error_val, kp);
+
+ return rc;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_donated_cpu() - Check if the provided CPU is already used by the enclave.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @cpu: CPU to check if already used.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * True if the provided CPU is already used by the enclave.
+ * * False otherwise.
+ */
+static bool ne_donated_cpu(struct ne_enclave *ne_enclave, unsigned int cpu)
+{
+ if (cpumask_test_cpu(cpu, ne_enclave->vcpu_ids))
+ return true;
+
+ return false;
+}
+
+/**
+ * ne_get_unused_core_from_cpu_pool() - Get the id of a full core from the
+ * NE CPU pool.
+ * @void: No parameters provided.
+ *
+ * Context: Process context. This function is called with the ne_enclave and
+ * ne_cpu_pool mutexes held.
+ * Return:
+ * * Core id.
+ * * -1 if no CPU core available in the pool.
+ */
+static int ne_get_unused_core_from_cpu_pool(void)
+{
+ int core_id = -1;
+ unsigned int i = 0;
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ if (!cpumask_empty(ne_cpu_pool.avail_threads_per_core[i])) {
+ core_id = i;
+
+ break;
+ }
+
+ return core_id;
+}
+
+/**
+ * ne_set_enclave_threads_per_core() - Set the threads of the provided core in
+ * the enclave data structure.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @core_id: Core id to get its threads from the NE CPU pool.
+ * @vcpu_id: vCPU id part of the provided core.
+ *
+ * Context: Process context. This function is called with the ne_enclave and
+ * ne_cpu_pool mutexes held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_set_enclave_threads_per_core(struct ne_enclave *ne_enclave,
+ int core_id, u32 vcpu_id)
+{
+ unsigned int cpu = 0;
+
+ if (core_id < 0 && vcpu_id == 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "No CPUs available in NE CPU pool\n");
+
+ return -NE_ERR_NO_CPUS_AVAIL_IN_POOL;
+ }
+
+ if (core_id < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "CPU %d is not in NE CPU pool\n", vcpu_id);
+
+ return -NE_ERR_VCPU_NOT_IN_CPU_POOL;
+ }
+
+ if (core_id >= ne_enclave->nr_parent_vm_cores) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Invalid core id %d - ne_enclave\n", core_id);
+
+ return -NE_ERR_VCPU_INVALID_CPU_CORE;
+ }
+
+ for_each_cpu(cpu, ne_cpu_pool.avail_threads_per_core[core_id])
+ cpumask_set_cpu(cpu, ne_enclave->threads_per_core[core_id]);
+
+ cpumask_clear(ne_cpu_pool.avail_threads_per_core[core_id]);
+
+ return 0;
+}
+
+/**
+ * ne_get_cpu_from_cpu_pool() - Get a CPU from the NE CPU pool, either from the
+ * remaining sibling(s) of a CPU core or the first
+ * sibling of a new CPU core.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @vcpu_id: vCPU to get from the NE CPU pool.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_get_cpu_from_cpu_pool(struct ne_enclave *ne_enclave, u32 *vcpu_id)
+{
+ int core_id = -1;
+ unsigned int cpu = 0;
+ unsigned int i = 0;
+ int rc = -EINVAL;
+
+ /*
+ * If previously allocated a thread of a core to this enclave, first
+ * check remaining sibling(s) for new CPU allocations, so that full
+ * CPU cores are used for the enclave.
+ */
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ for_each_cpu(cpu, ne_enclave->threads_per_core[i])
+ if (!ne_donated_cpu(ne_enclave, cpu)) {
+ *vcpu_id = cpu;
+
+ return 0;
+ }
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ /*
+ * If no remaining siblings, get a core from the NE CPU pool and keep
+ * track of all the threads in the enclave threads per core data structure.
+ */
+ core_id = ne_get_unused_core_from_cpu_pool();
+
+ rc = ne_set_enclave_threads_per_core(ne_enclave, core_id, *vcpu_id);
+ if (rc < 0)
+ goto unlock_mutex;
+
+ *vcpu_id = cpumask_any(ne_enclave->threads_per_core[core_id]);
+
+ rc = 0;
+
+unlock_mutex:
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return rc;
+}
+
+/**
+ * ne_get_vcpu_core_from_cpu_pool() - Get from the NE CPU pool the id of the
+ * core associated with the provided vCPU.
+ * @vcpu_id: Provided vCPU id to get its associated core id.
+ *
+ * Context: Process context. This function is called with the ne_enclave and
+ * ne_cpu_pool mutexes held.
+ * Return:
+ * * Core id.
+ * * -1 if the provided vCPU is not in the pool.
+ */
+static int ne_get_vcpu_core_from_cpu_pool(u32 vcpu_id)
+{
+ int core_id = -1;
+ unsigned int i = 0;
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ if (cpumask_test_cpu(vcpu_id, ne_cpu_pool.avail_threads_per_core[i])) {
+ core_id = i;
+
+ break;
+ }
+
+ return core_id;
+}
+
+/**
+ * ne_check_cpu_in_cpu_pool() - Check if the given vCPU is in the available CPUs
+ * from the pool.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @vcpu_id: ID of the vCPU to check if available in the NE CPU pool.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_check_cpu_in_cpu_pool(struct ne_enclave *ne_enclave, u32 vcpu_id)
+{
+ int core_id = -1;
+ unsigned int i = 0;
+ int rc = -EINVAL;
+
+ if (ne_donated_cpu(ne_enclave, vcpu_id)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "CPU %d already used\n", vcpu_id);
+
+ return -NE_ERR_VCPU_ALREADY_USED;
+ }
+
+ /*
+ * If previously allocated a thread of a core to this enclave, but not
+ * the full core, first check remaining sibling(s).
+ */
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ if (cpumask_test_cpu(vcpu_id, ne_enclave->threads_per_core[i]))
+ return 0;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ /*
+ * If no remaining siblings, get from the NE CPU pool the core
+ * associated with the vCPU and keep track of all the threads in the
+ * enclave threads per core data structure.
+ */
+ core_id = ne_get_vcpu_core_from_cpu_pool(vcpu_id);
+
+ rc = ne_set_enclave_threads_per_core(ne_enclave, core_id, vcpu_id);
+ if (rc < 0)
+ goto unlock_mutex;
+
+ rc = 0;
+
+unlock_mutex:
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return rc;
+}
+
+/**
+ * ne_add_vcpu_ioctl() - Add a vCPU to the slot associated with the current
+ * enclave.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @vcpu_id: ID of the CPU to be associated with the given slot,
+ * apic id on x86.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_add_vcpu_ioctl(struct ne_enclave *ne_enclave, u32 vcpu_id)
+{
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ struct pci_dev *pdev = ne_devs.ne_pci_dev->pdev;
+ int rc = -EINVAL;
+ struct slot_add_vcpu_req slot_add_vcpu_req = {};
+
+ if (ne_enclave->mm != current->mm)
+ return -EIO;
+
+ slot_add_vcpu_req.slot_uid = ne_enclave->slot_uid;
+ slot_add_vcpu_req.vcpu_id = vcpu_id;
+
+ rc = ne_do_request(pdev, SLOT_ADD_VCPU,
+ &slot_add_vcpu_req, sizeof(slot_add_vcpu_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in slot add vCPU [rc=%d]\n", rc);
+
+ return rc;
+ }
+
+ cpumask_set_cpu(vcpu_id, ne_enclave->vcpu_ids);
+
+ ne_enclave->nr_vcpus++;
+
+ return 0;
+}
+
+/**
+ * ne_sanity_check_user_mem_region() - Sanity check the user space memory
+ * region received during the set user
+ * memory region ioctl call.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @mem_region : User space memory region to be sanity checked.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_sanity_check_user_mem_region(struct ne_enclave *ne_enclave,
+ struct ne_user_memory_region mem_region)
+{
+ struct ne_mem_region *ne_mem_region = NULL;
+
+ if (ne_enclave->mm != current->mm)
+ return -EIO;
+
+ if (mem_region.memory_size & (NE_MIN_MEM_REGION_SIZE - 1)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "User space memory size is not multiple of 2 MiB\n");
+
+ return -NE_ERR_INVALID_MEM_REGION_SIZE;
+ }
+
+ if (!IS_ALIGNED(mem_region.userspace_addr, NE_MIN_MEM_REGION_SIZE)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "User space address is not 2 MiB aligned\n");
+
+ return -NE_ERR_UNALIGNED_MEM_REGION_ADDR;
+ }
+
+ if ((mem_region.userspace_addr & (NE_MIN_MEM_REGION_SIZE - 1)) ||
+ !access_ok((void __user *)(unsigned long)mem_region.userspace_addr,
+ mem_region.memory_size)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Invalid user space address range\n");
+
+ return -NE_ERR_INVALID_MEM_REGION_ADDR;
+ }
+
+ list_for_each_entry(ne_mem_region, &ne_enclave->mem_regions_list,
+ mem_region_list_entry) {
+ u64 memory_size = ne_mem_region->memory_size;
+ u64 userspace_addr = ne_mem_region->userspace_addr;
+
+ if ((userspace_addr <= mem_region.userspace_addr &&
+ mem_region.userspace_addr < (userspace_addr + memory_size)) ||
+ (mem_region.userspace_addr <= userspace_addr &&
+ (mem_region.userspace_addr + mem_region.memory_size) > userspace_addr)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "User space memory region already used\n");
+
+ return -NE_ERR_MEM_REGION_ALREADY_USED;
+ }
+ }
+
+ return 0;
+}
+
+/**
+ * ne_sanity_check_user_mem_region_page() - Sanity check a page from the user space
+ * memory region received during the set
+ * user memory region ioctl call.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @mem_region_page: Page from the user space memory region to be sanity checked.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_sanity_check_user_mem_region_page(struct ne_enclave *ne_enclave,
+ struct page *mem_region_page)
+{
+ if (!PageHuge(mem_region_page)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Not a hugetlbfs page\n");
+
+ return -NE_ERR_MEM_NOT_HUGE_PAGE;
+ }
+
+ if (page_size(mem_region_page) & (NE_MIN_MEM_REGION_SIZE - 1)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Page size not multiple of 2 MiB\n");
+
+ return -NE_ERR_INVALID_PAGE_SIZE;
+ }
+
+ if (ne_enclave->numa_node != page_to_nid(mem_region_page)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Page is not from NUMA node %d\n",
+ ne_enclave->numa_node);
+
+ return -NE_ERR_MEM_DIFFERENT_NUMA_NODE;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_sanity_check_phys_mem_region() - Sanity check the start address and the size
+ * of a physical memory region.
+ * @phys_mem_region_paddr : Physical start address of the region to be sanity checked.
+ * @phys_mem_region_size : Length of the region to be sanity checked.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_sanity_check_phys_mem_region(u64 phys_mem_region_paddr,
+ u64 phys_mem_region_size)
+{
+ if (phys_mem_region_size & (NE_MIN_MEM_REGION_SIZE - 1)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Physical mem region size is not multiple of 2 MiB\n");
+
+ return -EINVAL;
+ }
+
+ if (!IS_ALIGNED(phys_mem_region_paddr, NE_MIN_MEM_REGION_SIZE)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Physical mem region address is not 2 MiB aligned\n");
+
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_merge_phys_contig_memory_regions() - Add a memory region and merge the adjacent
+ * regions if they are physically contiguous.
+ * @phys_contig_regions : Private data associated with the contiguous physical memory regions.
+ * @page_paddr : Physical start address of the region to be added.
+ * @page_size : Length of the region to be added.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int
+ne_merge_phys_contig_memory_regions(struct ne_phys_contig_mem_regions *phys_contig_regions,
+ u64 page_paddr, u64 page_size)
+{
+ unsigned long num = phys_contig_regions->num;
+ int rc = 0;
+
+ rc = ne_sanity_check_phys_mem_region(page_paddr, page_size);
+ if (rc < 0)
+ return rc;
+
+ /* Physically contiguous, just merge */
+ if (num && (phys_contig_regions->regions[num - 1].end + 1) == page_paddr) {
+ phys_contig_regions->regions[num - 1].end += page_size;
+ } else {
+ phys_contig_regions->regions[num].start = page_paddr;
+ phys_contig_regions->regions[num].end = page_paddr + page_size - 1;
+ phys_contig_regions->num++;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_set_user_memory_region_ioctl() - Add user space memory region to the slot
+ * associated with the current enclave.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @mem_region : User space memory region to be associated with the given slot.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_set_user_memory_region_ioctl(struct ne_enclave *ne_enclave,
+ struct ne_user_memory_region mem_region)
+{
+ long gup_rc = 0;
+ unsigned long i = 0;
+ unsigned long max_nr_pages = 0;
+ unsigned long memory_size = 0;
+ struct ne_mem_region *ne_mem_region = NULL;
+ struct pci_dev *pdev = ne_devs.ne_pci_dev->pdev;
+ struct ne_phys_contig_mem_regions phys_contig_mem_regions = {};
+ int rc = -EINVAL;
+
+ rc = ne_sanity_check_user_mem_region(ne_enclave, mem_region);
+ if (rc < 0)
+ return rc;
+
+ ne_mem_region = kzalloc(sizeof(*ne_mem_region), GFP_KERNEL);
+ if (!ne_mem_region)
+ return -ENOMEM;
+
+ max_nr_pages = mem_region.memory_size / NE_MIN_MEM_REGION_SIZE;
+
+ ne_mem_region->pages = kcalloc(max_nr_pages, sizeof(*ne_mem_region->pages),
+ GFP_KERNEL);
+ if (!ne_mem_region->pages) {
+ rc = -ENOMEM;
+
+ goto free_mem_region;
+ }
+
+ phys_contig_mem_regions.regions = kcalloc(max_nr_pages,
+ sizeof(*phys_contig_mem_regions.regions),
+ GFP_KERNEL);
+ if (!phys_contig_mem_regions.regions) {
+ rc = -ENOMEM;
+
+ goto free_mem_region;
+ }
+
+ do {
+ i = ne_mem_region->nr_pages;
+
+ if (i == max_nr_pages) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Reached max nr of pages in the pages data struct\n");
+
+ rc = -ENOMEM;
+
+ goto put_pages;
+ }
+
+ gup_rc = get_user_pages_unlocked(mem_region.userspace_addr + memory_size, 1,
+ ne_mem_region->pages + i, FOLL_GET);
+
+ if (gup_rc < 0) {
+ rc = gup_rc;
+
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in get user pages [rc=%d]\n", rc);
+
+ goto put_pages;
+ }
+
+ rc = ne_sanity_check_user_mem_region_page(ne_enclave, ne_mem_region->pages[i]);
+ if (rc < 0)
+ goto put_pages;
+
+ rc = ne_merge_phys_contig_memory_regions(&phys_contig_mem_regions,
+ page_to_phys(ne_mem_region->pages[i]),
+ page_size(ne_mem_region->pages[i]));
+ if (rc < 0)
+ goto put_pages;
+
+ memory_size += page_size(ne_mem_region->pages[i]);
+
+ ne_mem_region->nr_pages++;
+ } while (memory_size < mem_region.memory_size);
+
+ if ((ne_enclave->nr_mem_regions + phys_contig_mem_regions.num) >
+ ne_enclave->max_mem_regions) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Reached max memory regions %lld\n",
+ ne_enclave->max_mem_regions);
+
+ rc = -NE_ERR_MEM_MAX_REGIONS;
+
+ goto put_pages;
+ }
+
+ for (i = 0; i < phys_contig_mem_regions.num; i++) {
+ u64 phys_region_addr = phys_contig_mem_regions.regions[i].start;
+ u64 phys_region_size = range_len(&phys_contig_mem_regions.regions[i]);
+
+ rc = ne_sanity_check_phys_mem_region(phys_region_addr, phys_region_size);
+ if (rc < 0)
+ goto put_pages;
+ }
+
+ ne_mem_region->memory_size = mem_region.memory_size;
+ ne_mem_region->userspace_addr = mem_region.userspace_addr;
+
+ list_add(&ne_mem_region->mem_region_list_entry, &ne_enclave->mem_regions_list);
+
+ for (i = 0; i < phys_contig_mem_regions.num; i++) {
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ struct slot_add_mem_req slot_add_mem_req = {};
+
+ slot_add_mem_req.slot_uid = ne_enclave->slot_uid;
+ slot_add_mem_req.paddr = phys_contig_mem_regions.regions[i].start;
+ slot_add_mem_req.size = range_len(&phys_contig_mem_regions.regions[i]);
+
+ rc = ne_do_request(pdev, SLOT_ADD_MEM,
+ &slot_add_mem_req, sizeof(slot_add_mem_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in slot add mem [rc=%d]\n", rc);
+
+ kfree(phys_contig_mem_regions.regions);
+
+ /*
+ * Exit here without put pages as memory regions may
+ * already been added.
+ */
+ return rc;
+ }
+
+ ne_enclave->mem_size += slot_add_mem_req.size;
+ ne_enclave->nr_mem_regions++;
+ }
+
+ kfree(phys_contig_mem_regions.regions);
+
+ return 0;
+
+put_pages:
+ for (i = 0; i < ne_mem_region->nr_pages; i++)
+ put_page(ne_mem_region->pages[i]);
+free_mem_region:
+ kfree(phys_contig_mem_regions.regions);
+ kfree(ne_mem_region->pages);
+ kfree(ne_mem_region);
+
+ return rc;
+}
+
+/**
+ * ne_start_enclave_ioctl() - Trigger enclave start after the enclave resources,
+ * such as memory and CPU, have been set.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @enclave_start_info : Enclave info that includes enclave cid and flags.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_start_enclave_ioctl(struct ne_enclave *ne_enclave,
+ struct ne_enclave_start_info *enclave_start_info)
+{
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ unsigned int cpu = 0;
+ struct enclave_start_req enclave_start_req = {};
+ unsigned int i = 0;
+ struct pci_dev *pdev = ne_devs.ne_pci_dev->pdev;
+ int rc = -EINVAL;
+
+ if (!ne_enclave->nr_mem_regions) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave has no mem regions\n");
+
+ return -NE_ERR_NO_MEM_REGIONS_ADDED;
+ }
+
+ if (ne_enclave->mem_size < NE_MIN_ENCLAVE_MEM_SIZE) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave memory is less than %ld\n",
+ NE_MIN_ENCLAVE_MEM_SIZE);
+
+ return -NE_ERR_ENCLAVE_MEM_MIN_SIZE;
+ }
+
+ if (!ne_enclave->nr_vcpus) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave has no vCPUs\n");
+
+ return -NE_ERR_NO_VCPUS_ADDED;
+ }
+
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ for_each_cpu(cpu, ne_enclave->threads_per_core[i])
+ if (!cpumask_test_cpu(cpu, ne_enclave->vcpu_ids)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Full CPU cores not used\n");
+
+ return -NE_ERR_FULL_CORES_NOT_USED;
+ }
+
+ enclave_start_req.enclave_cid = enclave_start_info->enclave_cid;
+ enclave_start_req.flags = enclave_start_info->flags;
+ enclave_start_req.slot_uid = ne_enclave->slot_uid;
+
+ rc = ne_do_request(pdev, ENCLAVE_START,
+ &enclave_start_req, sizeof(enclave_start_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in enclave start [rc=%d]\n", rc);
+
+ return rc;
+ }
+
+ ne_enclave->state = NE_STATE_RUNNING;
+
+ enclave_start_info->enclave_cid = cmd_reply.enclave_cid;
+
+ return 0;
+}
+
+/**
+ * ne_enclave_ioctl() - Ioctl function provided by the enclave file.
+ * @file: File associated with this ioctl function.
+ * @cmd: The command that is set for the ioctl call.
+ * @arg: The argument that is provided for the ioctl call.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static long ne_enclave_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ struct ne_enclave *ne_enclave = file->private_data;
+
+ switch (cmd) {
+ case NE_ADD_VCPU: {
+ int rc = -EINVAL;
+ u32 vcpu_id = 0;
+
+ if (copy_from_user(&vcpu_id, (void __user *)arg, sizeof(vcpu_id)))
+ return -EFAULT;
+
+ mutex_lock(&ne_enclave->enclave_info_mutex);
+
+ if (ne_enclave->state != NE_STATE_INIT) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave is not in init state\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_NOT_IN_INIT_STATE;
+ }
+
+ if (vcpu_id >= (ne_enclave->nr_parent_vm_cores *
+ ne_enclave->nr_threads_per_core)) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "vCPU id higher than max CPU id\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_INVALID_VCPU;
+ }
+
+ if (!vcpu_id) {
+ /* Use the CPU pool for choosing a CPU for the enclave. */
+ rc = ne_get_cpu_from_cpu_pool(ne_enclave, &vcpu_id);
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in get CPU from pool [rc=%d]\n",
+ rc);
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+ } else {
+ /* Check if the provided vCPU is available in the NE CPU pool. */
+ rc = ne_check_cpu_in_cpu_pool(ne_enclave, vcpu_id);
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in check CPU %d in pool [rc=%d]\n",
+ vcpu_id, rc);
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+ }
+
+ rc = ne_add_vcpu_ioctl(ne_enclave, vcpu_id);
+ if (rc < 0) {
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ if (copy_to_user((void __user *)arg, &vcpu_id, sizeof(vcpu_id)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ case NE_GET_IMAGE_LOAD_INFO: {
+ struct ne_image_load_info image_load_info = {};
+
+ if (copy_from_user(&image_load_info, (void __user *)arg, sizeof(image_load_info)))
+ return -EFAULT;
+
+ mutex_lock(&ne_enclave->enclave_info_mutex);
+
+ if (ne_enclave->state != NE_STATE_INIT) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave is not in init state\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_NOT_IN_INIT_STATE;
+ }
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ if (!image_load_info.flags ||
+ image_load_info.flags >= NE_IMAGE_LOAD_MAX_FLAG_VAL) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Incorrect flag in enclave image load info\n");
+
+ return -NE_ERR_INVALID_FLAG_VALUE;
+ }
+
+ if (image_load_info.flags == NE_EIF_IMAGE)
+ image_load_info.memory_offset = NE_EIF_LOAD_OFFSET;
+
+ if (copy_to_user((void __user *)arg, &image_load_info, sizeof(image_load_info)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ case NE_SET_USER_MEMORY_REGION: {
+ struct ne_user_memory_region mem_region = {};
+ int rc = -EINVAL;
+
+ if (copy_from_user(&mem_region, (void __user *)arg, sizeof(mem_region)))
+ return -EFAULT;
+
+ if (mem_region.flags >= NE_MEMORY_REGION_MAX_FLAG_VAL) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Incorrect flag for user memory region\n");
+
+ return -NE_ERR_INVALID_FLAG_VALUE;
+ }
+
+ mutex_lock(&ne_enclave->enclave_info_mutex);
+
+ if (ne_enclave->state != NE_STATE_INIT) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave is not in init state\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_NOT_IN_INIT_STATE;
+ }
+
+ rc = ne_set_user_memory_region_ioctl(ne_enclave, mem_region);
+ if (rc < 0) {
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return 0;
+ }
+
+ case NE_START_ENCLAVE: {
+ struct ne_enclave_start_info enclave_start_info = {};
+ int rc = -EINVAL;
+
+ if (copy_from_user(&enclave_start_info, (void __user *)arg,
+ sizeof(enclave_start_info)))
+ return -EFAULT;
+
+ if (enclave_start_info.flags >= NE_ENCLAVE_START_MAX_FLAG_VAL) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Incorrect flag in enclave start info\n");
+
+ return -NE_ERR_INVALID_FLAG_VALUE;
+ }
+
+ /*
+ * Do not use well-known CIDs - 0, 1, 2 - for enclaves.
+ * VMADDR_CID_ANY = -1U
+ * VMADDR_CID_HYPERVISOR = 0
+ * VMADDR_CID_LOCAL = 1
+ * VMADDR_CID_HOST = 2
+ * Note: 0 is used as a placeholder to auto-generate an enclave CID.
+ * http://man7.org/linux/man-pages/man7/vsock.7.html
+ */
+ if (enclave_start_info.enclave_cid > 0 &&
+ enclave_start_info.enclave_cid <= VMADDR_CID_HOST) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Well-known CID value, not to be used for enclaves\n");
+
+ return -NE_ERR_INVALID_ENCLAVE_CID;
+ }
+
+ if (enclave_start_info.enclave_cid == U32_MAX) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Well-known CID value, not to be used for enclaves\n");
+
+ return -NE_ERR_INVALID_ENCLAVE_CID;
+ }
+
+ /*
+ * Do not use the CID of the primary / parent VM for enclaves.
+ */
+ if (enclave_start_info.enclave_cid == NE_PARENT_VM_CID) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "CID of the parent VM, not to be used for enclaves\n");
+
+ return -NE_ERR_INVALID_ENCLAVE_CID;
+ }
+
+ /* 64-bit CIDs are not yet supported for the vsock device. */
+ if (enclave_start_info.enclave_cid > U32_MAX) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "64-bit CIDs not yet supported for the vsock device\n");
+
+ return -NE_ERR_INVALID_ENCLAVE_CID;
+ }
+
+ mutex_lock(&ne_enclave->enclave_info_mutex);
+
+ if (ne_enclave->state != NE_STATE_INIT) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Enclave is not in init state\n");
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return -NE_ERR_NOT_IN_INIT_STATE;
+ }
+
+ rc = ne_start_enclave_ioctl(ne_enclave, &enclave_start_info);
+ if (rc < 0) {
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ return rc;
+ }
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+
+ if (copy_to_user((void __user *)arg, &enclave_start_info,
+ sizeof(enclave_start_info)))
+ return -EFAULT;
+
+ return 0;
+ }
+
+ default:
+ return -ENOTTY;
+ }
+
+ return 0;
+}
+
+/**
+ * ne_enclave_remove_all_mem_region_entries() - Remove all memory region entries
+ * from the enclave data structure.
+ * @ne_enclave : Private data associated with the current enclave.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ */
+static void ne_enclave_remove_all_mem_region_entries(struct ne_enclave *ne_enclave)
+{
+ unsigned long i = 0;
+ struct ne_mem_region *ne_mem_region = NULL;
+ struct ne_mem_region *ne_mem_region_tmp = NULL;
+
+ list_for_each_entry_safe(ne_mem_region, ne_mem_region_tmp,
+ &ne_enclave->mem_regions_list,
+ mem_region_list_entry) {
+ list_del(&ne_mem_region->mem_region_list_entry);
+
+ for (i = 0; i < ne_mem_region->nr_pages; i++)
+ put_page(ne_mem_region->pages[i]);
+
+ kfree(ne_mem_region->pages);
+
+ kfree(ne_mem_region);
+ }
+}
+
+/**
+ * ne_enclave_remove_all_vcpu_id_entries() - Remove all vCPU id entries from
+ * the enclave data structure.
+ * @ne_enclave : Private data associated with the current enclave.
+ *
+ * Context: Process context. This function is called with the ne_enclave mutex held.
+ */
+static void ne_enclave_remove_all_vcpu_id_entries(struct ne_enclave *ne_enclave)
+{
+ unsigned int cpu = 0;
+ unsigned int i = 0;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++) {
+ for_each_cpu(cpu, ne_enclave->threads_per_core[i])
+ /* Update the available NE CPU pool. */
+ cpumask_set_cpu(cpu, ne_cpu_pool.avail_threads_per_core[i]);
+
+ free_cpumask_var(ne_enclave->threads_per_core[i]);
+ }
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ kfree(ne_enclave->threads_per_core);
+
+ free_cpumask_var(ne_enclave->vcpu_ids);
+}
+
+/**
+ * ne_pci_dev_remove_enclave_entry() - Remove the enclave entry from the data
+ * structure that is part of the NE PCI
+ * device private data.
+ * @ne_enclave : Private data associated with the current enclave.
+ * @ne_pci_dev : Private data associated with the PCI device.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev enclave
+ * mutex held.
+ */
+static void ne_pci_dev_remove_enclave_entry(struct ne_enclave *ne_enclave,
+ struct ne_pci_dev *ne_pci_dev)
+{
+ struct ne_enclave *ne_enclave_entry = NULL;
+ struct ne_enclave *ne_enclave_entry_tmp = NULL;
+
+ list_for_each_entry_safe(ne_enclave_entry, ne_enclave_entry_tmp,
+ &ne_pci_dev->enclaves_list, enclave_list_entry) {
+ if (ne_enclave_entry->slot_uid == ne_enclave->slot_uid) {
+ list_del(&ne_enclave_entry->enclave_list_entry);
+
+ break;
+ }
+ }
+}
+
+/**
+ * ne_enclave_release() - Release function provided by the enclave file.
+ * @inode: Inode associated with this file release function.
+ * @file: File associated with this release function.
+ *
+ * Context: Process context.
+ * Return:
+ * * 0 on success.
+ * * Negative return value on failure.
+ */
+static int ne_enclave_release(struct inode *inode, struct file *file)
+{
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ struct enclave_stop_req enclave_stop_request = {};
+ struct ne_enclave *ne_enclave = file->private_data;
+ struct ne_pci_dev *ne_pci_dev = ne_devs.ne_pci_dev;
+ struct pci_dev *pdev = ne_pci_dev->pdev;
+ int rc = -EINVAL;
+ struct slot_free_req slot_free_req = {};
+
+ if (!ne_enclave)
+ return 0;
+
+ /*
+ * Early exit in case there is an error in the enclave creation logic
+ * and fput() is called on the cleanup path.
+ */
+ if (!ne_enclave->slot_uid)
+ return 0;
+
+ /*
+ * Acquire the enclave list mutex before the enclave mutex
+ * in order to avoid deadlocks with @ref ne_event_work_handler.
+ */
+ mutex_lock(&ne_pci_dev->enclaves_list_mutex);
+ mutex_lock(&ne_enclave->enclave_info_mutex);
+
+ if (ne_enclave->state != NE_STATE_INIT && ne_enclave->state != NE_STATE_STOPPED) {
+ enclave_stop_request.slot_uid = ne_enclave->slot_uid;
+
+ rc = ne_do_request(pdev, ENCLAVE_STOP,
+ &enclave_stop_request, sizeof(enclave_stop_request),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in enclave stop [rc=%d]\n", rc);
+
+ goto unlock_mutex;
+ }
+
+ memset(&cmd_reply, 0, sizeof(cmd_reply));
+ }
+
+ slot_free_req.slot_uid = ne_enclave->slot_uid;
+
+ rc = ne_do_request(pdev, SLOT_FREE,
+ &slot_free_req, sizeof(slot_free_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in slot free [rc=%d]\n", rc);
+
+ goto unlock_mutex;
+ }
+
+ ne_pci_dev_remove_enclave_entry(ne_enclave, ne_pci_dev);
+ ne_enclave_remove_all_mem_region_entries(ne_enclave);
+ ne_enclave_remove_all_vcpu_id_entries(ne_enclave);
+
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+ mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+
+ kfree(ne_enclave);
+
+ return 0;
+
+unlock_mutex:
+ mutex_unlock(&ne_enclave->enclave_info_mutex);
+ mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+
+ return rc;
+}
+
+/**
+ * ne_enclave_poll() - Poll functionality used for enclave out-of-band events.
+ * @file: File associated with this poll function.
+ * @wait: Poll table data structure.
+ *
+ * Context: Process context.
+ * Return:
+ * * Poll mask.
+ */
+static __poll_t ne_enclave_poll(struct file *file, poll_table *wait)
+{
+ __poll_t mask = 0;
+ struct ne_enclave *ne_enclave = file->private_data;
+
+ poll_wait(file, &ne_enclave->eventq, wait);
+
+ if (ne_enclave->has_event)
+ mask |= EPOLLHUP;
+
+ return mask;
+}
+
+static const struct file_operations ne_enclave_fops = {
+ .owner = THIS_MODULE,
+ .llseek = noop_llseek,
+ .poll = ne_enclave_poll,
+ .unlocked_ioctl = ne_enclave_ioctl,
+ .release = ne_enclave_release,
+};
+
+/**
+ * ne_create_vm_ioctl() - Alloc slot to be associated with an enclave. Create
+ * enclave file descriptor to be further used for enclave
+ * resources handling e.g. memory regions and CPUs.
+ * @ne_pci_dev : Private data associated with the PCI device.
+ * @slot_uid: User pointer to store the generated unique slot id
+ * associated with an enclave to.
+ *
+ * Context: Process context. This function is called with the ne_pci_dev enclave
+ * mutex held.
+ * Return:
+ * * Enclave fd on success.
+ * * Negative return value on failure.
+ */
+static int ne_create_vm_ioctl(struct ne_pci_dev *ne_pci_dev, u64 __user *slot_uid)
+{
+ struct ne_pci_dev_cmd_reply cmd_reply = {};
+ int enclave_fd = -1;
+ struct file *enclave_file = NULL;
+ unsigned int i = 0;
+ struct ne_enclave *ne_enclave = NULL;
+ struct pci_dev *pdev = ne_pci_dev->pdev;
+ int rc = -EINVAL;
+ struct slot_alloc_req slot_alloc_req = {};
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ for (i = 0; i < ne_cpu_pool.nr_parent_vm_cores; i++)
+ if (!cpumask_empty(ne_cpu_pool.avail_threads_per_core[i]))
+ break;
+
+ if (i == ne_cpu_pool.nr_parent_vm_cores) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "No CPUs available in CPU pool\n");
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ return -NE_ERR_NO_CPUS_AVAIL_IN_POOL;
+ }
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ ne_enclave = kzalloc(sizeof(*ne_enclave), GFP_KERNEL);
+ if (!ne_enclave)
+ return -ENOMEM;
+
+ mutex_lock(&ne_cpu_pool.mutex);
+
+ ne_enclave->nr_parent_vm_cores = ne_cpu_pool.nr_parent_vm_cores;
+ ne_enclave->nr_threads_per_core = ne_cpu_pool.nr_threads_per_core;
+ ne_enclave->numa_node = ne_cpu_pool.numa_node;
+
+ mutex_unlock(&ne_cpu_pool.mutex);
+
+ ne_enclave->threads_per_core = kcalloc(ne_enclave->nr_parent_vm_cores,
+ sizeof(*ne_enclave->threads_per_core),
+ GFP_KERNEL);
+ if (!ne_enclave->threads_per_core) {
+ rc = -ENOMEM;
+
+ goto free_ne_enclave;
+ }
+
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ if (!zalloc_cpumask_var(&ne_enclave->threads_per_core[i], GFP_KERNEL)) {
+ rc = -ENOMEM;
+
+ goto free_cpumask;
+ }
+
+ if (!zalloc_cpumask_var(&ne_enclave->vcpu_ids, GFP_KERNEL)) {
+ rc = -ENOMEM;
+
+ goto free_cpumask;
+ }
+
+ enclave_fd = get_unused_fd_flags(O_CLOEXEC);
+ if (enclave_fd < 0) {
+ rc = enclave_fd;
+
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in getting unused fd [rc=%d]\n", rc);
+
+ goto free_cpumask;
+ }
+
+ enclave_file = anon_inode_getfile("ne-vm", &ne_enclave_fops, ne_enclave, O_RDWR);
+ if (IS_ERR(enclave_file)) {
+ rc = PTR_ERR(enclave_file);
+
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in anon inode get file [rc=%d]\n", rc);
+
+ goto put_fd;
+ }
+
+ rc = ne_do_request(pdev, SLOT_ALLOC,
+ &slot_alloc_req, sizeof(slot_alloc_req),
+ &cmd_reply, sizeof(cmd_reply));
+ if (rc < 0) {
+ dev_err_ratelimited(ne_misc_dev.this_device,
+ "Error in slot alloc [rc=%d]\n", rc);
+
+ goto put_file;
+ }
+
+ init_waitqueue_head(&ne_enclave->eventq);
+ ne_enclave->has_event = false;
+ mutex_init(&ne_enclave->enclave_info_mutex);
+ ne_enclave->max_mem_regions = cmd_reply.mem_regions;
+ INIT_LIST_HEAD(&ne_enclave->mem_regions_list);
+ ne_enclave->mm = current->mm;
+ ne_enclave->slot_uid = cmd_reply.slot_uid;
+ ne_enclave->state = NE_STATE_INIT;
+
+ list_add(&ne_enclave->enclave_list_entry, &ne_pci_dev->enclaves_list);
+
+ if (copy_to_user(slot_uid, &ne_enclave->slot_uid, sizeof(ne_enclave->slot_uid))) {
+ /*
+ * As we're holding the only reference to 'enclave_file', fput()
+ * will call ne_enclave_release() which will do a proper cleanup
+ * of all so far allocated resources, leaving only the unused fd
+ * for us to free.
+ */
+ fput(enclave_file);
+ put_unused_fd(enclave_fd);
+
+ return -EFAULT;
+ }
+
+ fd_install(enclave_fd, enclave_file);
+
+ return enclave_fd;
+
+put_file:
+ fput(enclave_file);
+put_fd:
+ put_unused_fd(enclave_fd);
+free_cpumask:
+ free_cpumask_var(ne_enclave->vcpu_ids);
+ for (i = 0; i < ne_enclave->nr_parent_vm_cores; i++)
+ free_cpumask_var(ne_enclave->threads_per_core[i]);
+ kfree(ne_enclave->threads_per_core);
+free_ne_enclave:
+ kfree(ne_enclave);
+
+ return rc;
+}
+
+/**
+ * ne_ioctl() - Ioctl function provided by the NE misc device.
+ * @file: File associated with this ioctl function.
+ * @cmd: The command that is set for the ioctl call.
+ * @arg: The argument that is provided for the ioctl call.
+ *
+ * Context: Process context.
+ * Return:
+ * * Ioctl result (e.g. enclave file descriptor) on success.
+ * * Negative return value on failure.
+ */
+static long ne_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case NE_CREATE_VM: {
+ int enclave_fd = -1;
+ struct ne_pci_dev *ne_pci_dev = ne_devs.ne_pci_dev;
+ u64 __user *slot_uid = (void __user *)arg;
+
+ mutex_lock(&ne_pci_dev->enclaves_list_mutex);
+ enclave_fd = ne_create_vm_ioctl(ne_pci_dev, slot_uid);
+ mutex_unlock(&ne_pci_dev->enclaves_list_mutex);
+
+ return enclave_fd;
+ }
+
+ default:
+ return -ENOTTY;
+ }
+
+ return 0;
+}
+
+#if defined(CONFIG_NITRO_ENCLAVES_MISC_DEV_TEST)
+#include "ne_misc_dev_test.c"
+#endif
+
+static int __init ne_init(void)
+{
+ mutex_init(&ne_cpu_pool.mutex);
+
+ return pci_register_driver(&ne_pci_driver);
+}
+
+static void __exit ne_exit(void)
+{
+ pci_unregister_driver(&ne_pci_driver);
+
+ ne_teardown_cpu_pool();
+}
+
+module_init(ne_init);
+module_exit(ne_exit);
+
+MODULE_AUTHOR("Amazon.com, Inc. or its affiliates");
+MODULE_DESCRIPTION("Nitro Enclaves Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev.h b/drivers/virt/nitro_enclaves/ne_misc_dev.h
new file mode 100644
index 000000000..2a4d2224b
--- /dev/null
+++ b/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_ */
diff --git a/drivers/virt/nitro_enclaves/ne_misc_dev_test.c b/drivers/virt/nitro_enclaves/ne_misc_dev_test.c
new file mode 100644
index 000000000..74df43b92
--- /dev/null
+++ b/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);
diff --git a/drivers/virt/nitro_enclaves/ne_pci_dev.c b/drivers/virt/nitro_enclaves/ne_pci_dev.c
new file mode 100644
index 000000000..6b81e8f3a
--- /dev/null
+++ b/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(sizeof(*ne_pci_dev), GFP_KERNEL);
+ 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,
+};
diff --git a/drivers/virt/nitro_enclaves/ne_pci_dev.h b/drivers/virt/nitro_enclaves/ne_pci_dev.h
new file mode 100644
index 000000000..6e9f28971
--- /dev/null
+++ b/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_ */
diff --git a/drivers/virt/vboxguest/Kconfig b/drivers/virt/vboxguest/Kconfig
new file mode 100644
index 000000000..cc329887b
--- /dev/null
+++ b/drivers/virt/vboxguest/Kconfig
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config VBOXGUEST
+ tristate "Virtual Box Guest integration support"
+ depends on X86 && PCI && INPUT
+ 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.
diff --git a/drivers/virt/vboxguest/Makefile b/drivers/virt/vboxguest/Makefile
new file mode 100644
index 000000000..804279216
--- /dev/null
+++ b/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
diff --git a/drivers/virt/vboxguest/vboxguest_core.c b/drivers/virt/vboxguest/vboxguest_core.c
new file mode 100644
index 000000000..dfd69bd77
--- /dev/null
+++ b/drivers/virt/vboxguest/vboxguest_core.c
@@ -0,0 +1,1826 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR CDDL-1.0) */
+/*
+ * vboxguest core guest-device handling code, VBoxGuest.cpp in upstream svn.
+ *
+ * Copyright (C) 2007-2016 Oracle Corporation
+ */
+
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/sizes.h>
+#include <linux/slab.h>
+#include <linux/vbox_err.h>
+#include <linux/vbox_utils.h>
+#include <linux/vmalloc.h>
+#include "vboxguest_core.h"
+#include "vboxguest_version.h"
+
+/* Get the pointer to the first HGCM parameter. */
+#define VBG_IOCTL_HGCM_CALL_PARMS(a) \
+ ((struct vmmdev_hgcm_function_parameter *)( \
+ (u8 *)(a) + sizeof(struct vbg_ioctl_hgcm_call)))
+/* Get the pointer to the first HGCM parameter in a 32-bit request. */
+#define VBG_IOCTL_HGCM_CALL_PARMS32(a) \
+ ((struct vmmdev_hgcm_function_parameter32 *)( \
+ (u8 *)(a) + sizeof(struct vbg_ioctl_hgcm_call)))
+
+#define GUEST_MAPPINGS_TRIES 5
+
+#define VBG_KERNEL_REQUEST \
+ (VMMDEV_REQUESTOR_KERNEL | VMMDEV_REQUESTOR_USR_DRV | \
+ VMMDEV_REQUESTOR_CON_DONT_KNOW | VMMDEV_REQUESTOR_TRUST_NOT_GIVEN)
+
+/**
+ * Reserves memory in which the VMM can relocate any guest mappings
+ * that are floating around.
+ *
+ * This operation is a little bit tricky since the VMM might not accept
+ * just any address because of address clashes between the three contexts
+ * it operates in, so we try several times.
+ *
+ * Failure to reserve the guest mappings is ignored.
+ *
+ * @gdev: The Guest extension device.
+ */
+static void vbg_guest_mappings_init(struct vbg_dev *gdev)
+{
+ struct vmmdev_hypervisorinfo *req;
+ void *guest_mappings[GUEST_MAPPINGS_TRIES];
+ struct page **pages = NULL;
+ u32 size, hypervisor_size;
+ int i, rc;
+
+ /* Query the required space. */
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HYPERVISOR_INFO,
+ VBG_KERNEL_REQUEST);
+ if (!req)
+ return;
+
+ req->hypervisor_start = 0;
+ req->hypervisor_size = 0;
+ rc = vbg_req_perform(gdev, req);
+ if (rc < 0)
+ goto out;
+
+ /*
+ * The VMM will report back if there is nothing it wants to map, like
+ * for instance in VT-x and AMD-V mode.
+ */
+ if (req->hypervisor_size == 0)
+ goto out;
+
+ hypervisor_size = req->hypervisor_size;
+ /* Add 4M so that we can align the vmap to 4MiB as the host requires. */
+ size = PAGE_ALIGN(req->hypervisor_size) + SZ_4M;
+
+ pages = kmalloc_array(size >> PAGE_SHIFT, sizeof(*pages), GFP_KERNEL);
+ if (!pages)
+ goto out;
+
+ gdev->guest_mappings_dummy_page = alloc_page(GFP_HIGHUSER);
+ if (!gdev->guest_mappings_dummy_page)
+ goto out;
+
+ for (i = 0; i < (size >> PAGE_SHIFT); i++)
+ pages[i] = gdev->guest_mappings_dummy_page;
+
+ /*
+ * Try several times, the VMM might not accept some addresses because
+ * of address clashes between the three contexts.
+ */
+ for (i = 0; i < GUEST_MAPPINGS_TRIES; i++) {
+ guest_mappings[i] = vmap(pages, (size >> PAGE_SHIFT),
+ VM_MAP, PAGE_KERNEL_RO);
+ if (!guest_mappings[i])
+ break;
+
+ req->header.request_type = VMMDEVREQ_SET_HYPERVISOR_INFO;
+ req->header.rc = VERR_INTERNAL_ERROR;
+ req->hypervisor_size = hypervisor_size;
+ req->hypervisor_start =
+ (unsigned long)PTR_ALIGN(guest_mappings[i], SZ_4M);
+
+ rc = vbg_req_perform(gdev, req);
+ if (rc >= 0) {
+ gdev->guest_mappings = guest_mappings[i];
+ break;
+ }
+ }
+
+ /* Free vmap's from failed attempts. */
+ while (--i >= 0)
+ vunmap(guest_mappings[i]);
+
+ /* On failure free the dummy-page backing the vmap */
+ if (!gdev->guest_mappings) {
+ __free_page(gdev->guest_mappings_dummy_page);
+ gdev->guest_mappings_dummy_page = NULL;
+ }
+
+out:
+ vbg_req_free(req, sizeof(*req));
+ kfree(pages);
+}
+
+/**
+ * Undo what vbg_guest_mappings_init did.
+ *
+ * @gdev: The Guest extension device.
+ */
+static void vbg_guest_mappings_exit(struct vbg_dev *gdev)
+{
+ struct vmmdev_hypervisorinfo *req;
+ int rc;
+
+ if (!gdev->guest_mappings)
+ return;
+
+ /*
+ * Tell the host that we're going to free the memory we reserved for
+ * it, the free it up. (Leak the memory if anything goes wrong here.)
+ */
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_HYPERVISOR_INFO,
+ VBG_KERNEL_REQUEST);
+ if (!req)
+ return;
+
+ req->hypervisor_start = 0;
+ req->hypervisor_size = 0;
+
+ rc = vbg_req_perform(gdev, req);
+
+ vbg_req_free(req, sizeof(*req));
+
+ if (rc < 0) {
+ vbg_err("%s error: %d\n", __func__, rc);
+ return;
+ }
+
+ vunmap(gdev->guest_mappings);
+ gdev->guest_mappings = NULL;
+
+ __free_page(gdev->guest_mappings_dummy_page);
+ gdev->guest_mappings_dummy_page = NULL;
+}
+
+/**
+ * Report the guest information to the host.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ */
+static int vbg_report_guest_info(struct vbg_dev *gdev)
+{
+ /*
+ * Allocate and fill in the two guest info reports.
+ */
+ struct vmmdev_guest_info *req1 = NULL;
+ struct vmmdev_guest_info2 *req2 = NULL;
+ int rc, ret = -ENOMEM;
+
+ req1 = vbg_req_alloc(sizeof(*req1), VMMDEVREQ_REPORT_GUEST_INFO,
+ VBG_KERNEL_REQUEST);
+ req2 = vbg_req_alloc(sizeof(*req2), VMMDEVREQ_REPORT_GUEST_INFO2,
+ VBG_KERNEL_REQUEST);
+ if (!req1 || !req2)
+ goto out_free;
+
+ req1->interface_version = VMMDEV_VERSION;
+ req1->os_type = VMMDEV_OSTYPE_LINUX26;
+#if __BITS_PER_LONG == 64
+ req1->os_type |= VMMDEV_OSTYPE_X64;
+#endif
+
+ req2->additions_major = VBG_VERSION_MAJOR;
+ req2->additions_minor = VBG_VERSION_MINOR;
+ req2->additions_build = VBG_VERSION_BUILD;
+ req2->additions_revision = VBG_SVN_REV;
+ req2->additions_features =
+ VMMDEV_GUEST_INFO2_ADDITIONS_FEATURES_REQUESTOR_INFO;
+ strscpy(req2->name, VBG_VERSION_STRING,
+ sizeof(req2->name));
+
+ /*
+ * There are two protocols here:
+ * 1. INFO2 + INFO1. Supported by >=3.2.51.
+ * 2. INFO1 and optionally INFO2. The old protocol.
+ *
+ * We try protocol 2 first. It will fail with VERR_NOT_SUPPORTED
+ * if not supported by the VMMDev (message ordering requirement).
+ */
+ rc = vbg_req_perform(gdev, req2);
+ if (rc >= 0) {
+ rc = vbg_req_perform(gdev, req1);
+ } else if (rc == VERR_NOT_SUPPORTED || rc == VERR_NOT_IMPLEMENTED) {
+ rc = vbg_req_perform(gdev, req1);
+ if (rc >= 0) {
+ rc = vbg_req_perform(gdev, req2);
+ if (rc == VERR_NOT_IMPLEMENTED)
+ rc = VINF_SUCCESS;
+ }
+ }
+ ret = vbg_status_code_to_errno(rc);
+
+out_free:
+ vbg_req_free(req2, sizeof(*req2));
+ vbg_req_free(req1, sizeof(*req1));
+ return ret;
+}
+
+/**
+ * Report the guest driver status to the host.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @active: Flag whether the driver is now active or not.
+ */
+static int vbg_report_driver_status(struct vbg_dev *gdev, bool active)
+{
+ struct vmmdev_guest_status *req;
+ int rc;
+
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_REPORT_GUEST_STATUS,
+ VBG_KERNEL_REQUEST);
+ if (!req)
+ return -ENOMEM;
+
+ req->facility = VBOXGUEST_FACILITY_TYPE_VBOXGUEST_DRIVER;
+ if (active)
+ req->status = VBOXGUEST_FACILITY_STATUS_ACTIVE;
+ else
+ req->status = VBOXGUEST_FACILITY_STATUS_INACTIVE;
+ req->flags = 0;
+
+ rc = vbg_req_perform(gdev, req);
+ if (rc == VERR_NOT_IMPLEMENTED) /* Compatibility with older hosts. */
+ rc = VINF_SUCCESS;
+
+ vbg_req_free(req, sizeof(*req));
+
+ return vbg_status_code_to_errno(rc);
+}
+
+/**
+ * Inflate the balloon by one chunk. The caller owns the balloon mutex.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @chunk_idx: Index of the chunk.
+ */
+static int vbg_balloon_inflate(struct vbg_dev *gdev, u32 chunk_idx)
+{
+ struct vmmdev_memballoon_change *req = gdev->mem_balloon.change_req;
+ struct page **pages;
+ int i, rc, ret;
+
+ pages = kmalloc_array(VMMDEV_MEMORY_BALLOON_CHUNK_PAGES,
+ sizeof(*pages),
+ GFP_KERNEL | __GFP_NOWARN);
+ if (!pages)
+ return -ENOMEM;
+
+ req->header.size = sizeof(*req);
+ req->inflate = true;
+ req->pages = VMMDEV_MEMORY_BALLOON_CHUNK_PAGES;
+
+ for (i = 0; i < VMMDEV_MEMORY_BALLOON_CHUNK_PAGES; i++) {
+ pages[i] = alloc_page(GFP_KERNEL | __GFP_NOWARN);
+ if (!pages[i]) {
+ ret = -ENOMEM;
+ goto out_error;
+ }
+
+ req->phys_page[i] = page_to_phys(pages[i]);
+ }
+
+ rc = vbg_req_perform(gdev, req);
+ if (rc < 0) {
+ vbg_err("%s error, rc: %d\n", __func__, rc);
+ ret = vbg_status_code_to_errno(rc);
+ goto out_error;
+ }
+
+ gdev->mem_balloon.pages[chunk_idx] = pages;
+
+ return 0;
+
+out_error:
+ while (--i >= 0)
+ __free_page(pages[i]);
+ kfree(pages);
+
+ return ret;
+}
+
+/**
+ * Deflate the balloon by one chunk. The caller owns the balloon mutex.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @chunk_idx: Index of the chunk.
+ */
+static int vbg_balloon_deflate(struct vbg_dev *gdev, u32 chunk_idx)
+{
+ struct vmmdev_memballoon_change *req = gdev->mem_balloon.change_req;
+ struct page **pages = gdev->mem_balloon.pages[chunk_idx];
+ int i, rc;
+
+ req->header.size = sizeof(*req);
+ req->inflate = false;
+ req->pages = VMMDEV_MEMORY_BALLOON_CHUNK_PAGES;
+
+ for (i = 0; i < VMMDEV_MEMORY_BALLOON_CHUNK_PAGES; i++)
+ req->phys_page[i] = page_to_phys(pages[i]);
+
+ rc = vbg_req_perform(gdev, req);
+ if (rc < 0) {
+ vbg_err("%s error, rc: %d\n", __func__, rc);
+ return vbg_status_code_to_errno(rc);
+ }
+
+ for (i = 0; i < VMMDEV_MEMORY_BALLOON_CHUNK_PAGES; i++)
+ __free_page(pages[i]);
+ kfree(pages);
+ gdev->mem_balloon.pages[chunk_idx] = NULL;
+
+ return 0;
+}
+
+/**
+ * Respond to VMMDEV_EVENT_BALLOON_CHANGE_REQUEST events, query the size
+ * the host wants the balloon to be and adjust accordingly.
+ */
+static void vbg_balloon_work(struct work_struct *work)
+{
+ struct vbg_dev *gdev =
+ container_of(work, struct vbg_dev, mem_balloon.work);
+ struct vmmdev_memballoon_info *req = gdev->mem_balloon.get_req;
+ u32 i, chunks;
+ int rc, ret;
+
+ /*
+ * Setting this bit means that we request the value from the host and
+ * change the guest memory balloon according to the returned value.
+ */
+ req->event_ack = VMMDEV_EVENT_BALLOON_CHANGE_REQUEST;
+ rc = vbg_req_perform(gdev, req);
+ if (rc < 0) {
+ vbg_err("%s error, rc: %d)\n", __func__, rc);
+ return;
+ }
+
+ /*
+ * The host always returns the same maximum amount of chunks, so
+ * we do this once.
+ */
+ if (!gdev->mem_balloon.max_chunks) {
+ gdev->mem_balloon.pages =
+ devm_kcalloc(gdev->dev, req->phys_mem_chunks,
+ sizeof(struct page **), GFP_KERNEL);
+ if (!gdev->mem_balloon.pages)
+ return;
+
+ gdev->mem_balloon.max_chunks = req->phys_mem_chunks;
+ }
+
+ chunks = req->balloon_chunks;
+ if (chunks > gdev->mem_balloon.max_chunks) {
+ vbg_err("%s: illegal balloon size %u (max=%u)\n",
+ __func__, chunks, gdev->mem_balloon.max_chunks);
+ return;
+ }
+
+ if (chunks > gdev->mem_balloon.chunks) {
+ /* inflate */
+ for (i = gdev->mem_balloon.chunks; i < chunks; i++) {
+ ret = vbg_balloon_inflate(gdev, i);
+ if (ret < 0)
+ return;
+
+ gdev->mem_balloon.chunks++;
+ }
+ } else {
+ /* deflate */
+ for (i = gdev->mem_balloon.chunks; i-- > chunks;) {
+ ret = vbg_balloon_deflate(gdev, i);
+ if (ret < 0)
+ return;
+
+ gdev->mem_balloon.chunks--;
+ }
+ }
+}
+
+/**
+ * Callback for heartbeat timer.
+ */
+static void vbg_heartbeat_timer(struct timer_list *t)
+{
+ struct vbg_dev *gdev = from_timer(gdev, t, heartbeat_timer);
+
+ vbg_req_perform(gdev, gdev->guest_heartbeat_req);
+ mod_timer(&gdev->heartbeat_timer,
+ msecs_to_jiffies(gdev->heartbeat_interval_ms));
+}
+
+/**
+ * Configure the host to check guest's heartbeat
+ * and get heartbeat interval from the host.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @enabled: Set true to enable guest heartbeat checks on host.
+ */
+static int vbg_heartbeat_host_config(struct vbg_dev *gdev, bool enabled)
+{
+ struct vmmdev_heartbeat *req;
+ int rc;
+
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_HEARTBEAT_CONFIGURE,
+ VBG_KERNEL_REQUEST);
+ if (!req)
+ return -ENOMEM;
+
+ req->enabled = enabled;
+ req->interval_ns = 0;
+ rc = vbg_req_perform(gdev, req);
+ do_div(req->interval_ns, 1000000); /* ns -> ms */
+ gdev->heartbeat_interval_ms = req->interval_ns;
+ vbg_req_free(req, sizeof(*req));
+
+ return vbg_status_code_to_errno(rc);
+}
+
+/**
+ * Initializes the heartbeat timer. This feature may be disabled by the host.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ */
+static int vbg_heartbeat_init(struct vbg_dev *gdev)
+{
+ int ret;
+
+ /* Make sure that heartbeat checking is disabled if we fail. */
+ ret = vbg_heartbeat_host_config(gdev, false);
+ if (ret < 0)
+ return ret;
+
+ ret = vbg_heartbeat_host_config(gdev, true);
+ if (ret < 0)
+ return ret;
+
+ gdev->guest_heartbeat_req = vbg_req_alloc(
+ sizeof(*gdev->guest_heartbeat_req),
+ VMMDEVREQ_GUEST_HEARTBEAT,
+ VBG_KERNEL_REQUEST);
+ if (!gdev->guest_heartbeat_req)
+ return -ENOMEM;
+
+ vbg_info("%s: Setting up heartbeat to trigger every %d milliseconds\n",
+ __func__, gdev->heartbeat_interval_ms);
+ mod_timer(&gdev->heartbeat_timer, 0);
+
+ return 0;
+}
+
+/**
+ * Cleanup hearbeat code, stop HB timer and disable host heartbeat checking.
+ * @gdev: The Guest extension device.
+ */
+static void vbg_heartbeat_exit(struct vbg_dev *gdev)
+{
+ del_timer_sync(&gdev->heartbeat_timer);
+ vbg_heartbeat_host_config(gdev, false);
+ vbg_req_free(gdev->guest_heartbeat_req,
+ sizeof(*gdev->guest_heartbeat_req));
+}
+
+/**
+ * Applies a change to the bit usage tracker.
+ * Return: true if the mask changed, false if not.
+ * @tracker: The bit usage tracker.
+ * @changed: The bits to change.
+ * @previous: The previous value of the bits.
+ */
+static bool vbg_track_bit_usage(struct vbg_bit_usage_tracker *tracker,
+ u32 changed, u32 previous)
+{
+ bool global_change = false;
+
+ while (changed) {
+ u32 bit = ffs(changed) - 1;
+ u32 bitmask = BIT(bit);
+
+ if (bitmask & previous) {
+ tracker->per_bit_usage[bit] -= 1;
+ if (tracker->per_bit_usage[bit] == 0) {
+ global_change = true;
+ tracker->mask &= ~bitmask;
+ }
+ } else {
+ tracker->per_bit_usage[bit] += 1;
+ if (tracker->per_bit_usage[bit] == 1) {
+ global_change = true;
+ tracker->mask |= bitmask;
+ }
+ }
+
+ changed &= ~bitmask;
+ }
+
+ return global_change;
+}
+
+/**
+ * Init and termination worker for resetting the (host) event filter on the host
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @fixed_events: Fixed events (init time).
+ */
+static int vbg_reset_host_event_filter(struct vbg_dev *gdev,
+ u32 fixed_events)
+{
+ struct vmmdev_mask *req;
+ int rc;
+
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK,
+ VBG_KERNEL_REQUEST);
+ if (!req)
+ return -ENOMEM;
+
+ req->not_mask = U32_MAX & ~fixed_events;
+ req->or_mask = fixed_events;
+ rc = vbg_req_perform(gdev, req);
+ if (rc < 0)
+ vbg_err("%s error, rc: %d\n", __func__, rc);
+
+ vbg_req_free(req, sizeof(*req));
+ return vbg_status_code_to_errno(rc);
+}
+
+/**
+ * Changes the event filter mask for the given session.
+ *
+ * This is called in response to VBG_IOCTL_CHANGE_FILTER_MASK as well as to
+ * do session cleanup. Takes the session mutex.
+ *
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @session: The session.
+ * @or_mask: The events to add.
+ * @not_mask: The events to remove.
+ * @session_termination: Set if we're called by the session cleanup code.
+ * This tweaks the error handling so we perform
+ * proper session cleanup even if the host
+ * misbehaves.
+ */
+static int vbg_set_session_event_filter(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ u32 or_mask, u32 not_mask,
+ bool session_termination)
+{
+ struct vmmdev_mask *req;
+ u32 changed, previous;
+ int rc, ret = 0;
+
+ /*
+ * Allocate a request buffer before taking the spinlock, when
+ * the session is being terminated the requestor is the kernel,
+ * as we're cleaning up.
+ */
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_CTL_GUEST_FILTER_MASK,
+ session_termination ? VBG_KERNEL_REQUEST :
+ session->requestor);
+ if (!req) {
+ if (!session_termination)
+ return -ENOMEM;
+ /* Ignore allocation failure, we must do session cleanup. */
+ }
+
+ mutex_lock(&gdev->session_mutex);
+
+ /* Apply the changes to the session mask. */
+ previous = session->event_filter;
+ session->event_filter |= or_mask;
+ session->event_filter &= ~not_mask;
+
+ /* If anything actually changed, update the global usage counters. */
+ changed = previous ^ session->event_filter;
+ if (!changed)
+ goto out;
+
+ vbg_track_bit_usage(&gdev->event_filter_tracker, changed, previous);
+ or_mask = gdev->fixed_events | gdev->event_filter_tracker.mask;
+
+ if (gdev->event_filter_host == or_mask || !req)
+ goto out;
+
+ gdev->event_filter_host = or_mask;
+ req->or_mask = or_mask;
+ req->not_mask = ~or_mask;
+ rc = vbg_req_perform(gdev, req);
+ if (rc < 0) {
+ ret = vbg_status_code_to_errno(rc);
+
+ /* Failed, roll back (unless it's session termination time). */
+ gdev->event_filter_host = U32_MAX;
+ if (session_termination)
+ goto out;
+
+ vbg_track_bit_usage(&gdev->event_filter_tracker, changed,
+ session->event_filter);
+ session->event_filter = previous;
+ }
+
+out:
+ mutex_unlock(&gdev->session_mutex);
+ vbg_req_free(req, sizeof(*req));
+
+ return ret;
+}
+
+/**
+ * Init and termination worker for set guest capabilities to zero on the host.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ */
+static int vbg_reset_host_capabilities(struct vbg_dev *gdev)
+{
+ struct vmmdev_mask *req;
+ int rc;
+
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES,
+ VBG_KERNEL_REQUEST);
+ if (!req)
+ return -ENOMEM;
+
+ req->not_mask = U32_MAX;
+ req->or_mask = 0;
+ rc = vbg_req_perform(gdev, req);
+ if (rc < 0)
+ vbg_err("%s error, rc: %d\n", __func__, rc);
+
+ vbg_req_free(req, sizeof(*req));
+ return vbg_status_code_to_errno(rc);
+}
+
+/**
+ * Set guest capabilities on the host.
+ * Must be called with gdev->session_mutex hold.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @session: The session.
+ * @session_termination: Set if we're called by the session cleanup code.
+ */
+static int vbg_set_host_capabilities(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ bool session_termination)
+{
+ struct vmmdev_mask *req;
+ u32 caps;
+ int rc;
+
+ WARN_ON(!mutex_is_locked(&gdev->session_mutex));
+
+ caps = gdev->acquired_guest_caps | gdev->set_guest_caps_tracker.mask;
+
+ if (gdev->guest_caps_host == caps)
+ return 0;
+
+ /* On termination the requestor is the kernel, as we're cleaning up. */
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_GUEST_CAPABILITIES,
+ session_termination ? VBG_KERNEL_REQUEST :
+ session->requestor);
+ if (!req) {
+ gdev->guest_caps_host = U32_MAX;
+ return -ENOMEM;
+ }
+
+ req->or_mask = caps;
+ req->not_mask = ~caps;
+ rc = vbg_req_perform(gdev, req);
+ vbg_req_free(req, sizeof(*req));
+
+ gdev->guest_caps_host = (rc >= 0) ? caps : U32_MAX;
+
+ return vbg_status_code_to_errno(rc);
+}
+
+/**
+ * Acquire (get exclusive access) guest capabilities for a session.
+ * Takes the session mutex.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @session: The session.
+ * @flags: Flags (VBGL_IOC_AGC_FLAGS_XXX).
+ * @or_mask: The capabilities to add.
+ * @not_mask: The capabilities to remove.
+ * @session_termination: Set if we're called by the session cleanup code.
+ * This tweaks the error handling so we perform
+ * proper session cleanup even if the host
+ * misbehaves.
+ */
+static int vbg_acquire_session_capabilities(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ u32 or_mask, u32 not_mask,
+ u32 flags, bool session_termination)
+{
+ unsigned long irqflags;
+ bool wakeup = false;
+ int ret = 0;
+
+ mutex_lock(&gdev->session_mutex);
+
+ if (gdev->set_guest_caps_tracker.mask & or_mask) {
+ vbg_err("%s error: cannot acquire caps which are currently set\n",
+ __func__);
+ ret = -EINVAL;
+ goto out;
+ }
+
+ /*
+ * Mark any caps in the or_mask as now being in acquire-mode. Note
+ * once caps are in acquire_mode they always stay in this mode.
+ * This impacts event handling, so we take the event-lock.
+ */
+ spin_lock_irqsave(&gdev->event_spinlock, irqflags);
+ gdev->acquire_mode_guest_caps |= or_mask;
+ spin_unlock_irqrestore(&gdev->event_spinlock, irqflags);
+
+ /* If we only have to switch the caps to acquire mode, we're done. */
+ if (flags & VBGL_IOC_AGC_FLAGS_CONFIG_ACQUIRE_MODE)
+ goto out;
+
+ not_mask &= ~or_mask; /* or_mask takes priority over not_mask */
+ not_mask &= session->acquired_guest_caps;
+ or_mask &= ~session->acquired_guest_caps;
+
+ if (or_mask == 0 && not_mask == 0)
+ goto out;
+
+ if (gdev->acquired_guest_caps & or_mask) {
+ ret = -EBUSY;
+ goto out;
+ }
+
+ gdev->acquired_guest_caps |= or_mask;
+ gdev->acquired_guest_caps &= ~not_mask;
+ /* session->acquired_guest_caps impacts event handling, take the lock */
+ spin_lock_irqsave(&gdev->event_spinlock, irqflags);
+ session->acquired_guest_caps |= or_mask;
+ session->acquired_guest_caps &= ~not_mask;
+ spin_unlock_irqrestore(&gdev->event_spinlock, irqflags);
+
+ ret = vbg_set_host_capabilities(gdev, session, session_termination);
+ /* Roll back on failure, unless it's session termination time. */
+ if (ret < 0 && !session_termination) {
+ gdev->acquired_guest_caps &= ~or_mask;
+ gdev->acquired_guest_caps |= not_mask;
+ spin_lock_irqsave(&gdev->event_spinlock, irqflags);
+ session->acquired_guest_caps &= ~or_mask;
+ session->acquired_guest_caps |= not_mask;
+ spin_unlock_irqrestore(&gdev->event_spinlock, irqflags);
+ }
+
+ /*
+ * If we added a capability, check if that means some other thread in
+ * our session should be unblocked because there are events pending
+ * (the result of vbg_get_allowed_event_mask_for_session() may change).
+ *
+ * HACK ALERT! When the seamless support capability is added we generate
+ * a seamless change event so that the ring-3 client can sync with
+ * the seamless state.
+ */
+ if (ret == 0 && or_mask != 0) {
+ spin_lock_irqsave(&gdev->event_spinlock, irqflags);
+
+ if (or_mask & VMMDEV_GUEST_SUPPORTS_SEAMLESS)
+ gdev->pending_events |=
+ VMMDEV_EVENT_SEAMLESS_MODE_CHANGE_REQUEST;
+
+ if (gdev->pending_events)
+ wakeup = true;
+
+ spin_unlock_irqrestore(&gdev->event_spinlock, irqflags);
+
+ if (wakeup)
+ wake_up(&gdev->event_wq);
+ }
+
+out:
+ mutex_unlock(&gdev->session_mutex);
+
+ return ret;
+}
+
+/**
+ * Sets the guest capabilities for a session. Takes the session mutex.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @session: The session.
+ * @or_mask: The capabilities to add.
+ * @not_mask: The capabilities to remove.
+ * @session_termination: Set if we're called by the session cleanup code.
+ * This tweaks the error handling so we perform
+ * proper session cleanup even if the host
+ * misbehaves.
+ */
+static int vbg_set_session_capabilities(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ u32 or_mask, u32 not_mask,
+ bool session_termination)
+{
+ u32 changed, previous;
+ int ret = 0;
+
+ mutex_lock(&gdev->session_mutex);
+
+ if (gdev->acquire_mode_guest_caps & or_mask) {
+ vbg_err("%s error: cannot set caps which are in acquire_mode\n",
+ __func__);
+ ret = -EBUSY;
+ goto out;
+ }
+
+ /* Apply the changes to the session mask. */
+ previous = session->set_guest_caps;
+ session->set_guest_caps |= or_mask;
+ session->set_guest_caps &= ~not_mask;
+
+ /* If anything actually changed, update the global usage counters. */
+ changed = previous ^ session->set_guest_caps;
+ if (!changed)
+ goto out;
+
+ vbg_track_bit_usage(&gdev->set_guest_caps_tracker, changed, previous);
+
+ ret = vbg_set_host_capabilities(gdev, session, session_termination);
+ /* Roll back on failure, unless it's session termination time. */
+ if (ret < 0 && !session_termination) {
+ vbg_track_bit_usage(&gdev->set_guest_caps_tracker, changed,
+ session->set_guest_caps);
+ session->set_guest_caps = previous;
+ }
+
+out:
+ mutex_unlock(&gdev->session_mutex);
+
+ return ret;
+}
+
+/**
+ * vbg_query_host_version get the host feature mask and version information.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ */
+static int vbg_query_host_version(struct vbg_dev *gdev)
+{
+ struct vmmdev_host_version *req;
+ int rc, ret;
+
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_GET_HOST_VERSION,
+ VBG_KERNEL_REQUEST);
+ if (!req)
+ return -ENOMEM;
+
+ rc = vbg_req_perform(gdev, req);
+ ret = vbg_status_code_to_errno(rc);
+ if (ret) {
+ vbg_err("%s error: %d\n", __func__, rc);
+ goto out;
+ }
+
+ snprintf(gdev->host_version, sizeof(gdev->host_version), "%u.%u.%ur%u",
+ req->major, req->minor, req->build, req->revision);
+ gdev->host_features = req->features;
+
+ vbg_info("vboxguest: host-version: %s %#x\n", gdev->host_version,
+ gdev->host_features);
+
+ if (!(req->features & VMMDEV_HVF_HGCM_PHYS_PAGE_LIST)) {
+ vbg_err("vboxguest: Error host too old (does not support page-lists)\n");
+ ret = -ENODEV;
+ }
+
+out:
+ vbg_req_free(req, sizeof(*req));
+ return ret;
+}
+
+/**
+ * Initializes the VBoxGuest device extension when the
+ * device driver is loaded.
+ *
+ * The native code locates the VMMDev on the PCI bus and retrieve
+ * the MMIO and I/O port ranges, this function will take care of
+ * mapping the MMIO memory (if present). Upon successful return
+ * the native code should set up the interrupt handler.
+ *
+ * Return: 0 or negative errno value.
+ *
+ * @gdev: The Guest extension device.
+ * @fixed_events: Events that will be enabled upon init and no client
+ * will ever be allowed to mask.
+ */
+int vbg_core_init(struct vbg_dev *gdev, u32 fixed_events)
+{
+ int ret = -ENOMEM;
+
+ gdev->fixed_events = fixed_events | VMMDEV_EVENT_HGCM;
+ gdev->event_filter_host = U32_MAX; /* forces a report */
+ gdev->guest_caps_host = U32_MAX; /* forces a report */
+
+ init_waitqueue_head(&gdev->event_wq);
+ init_waitqueue_head(&gdev->hgcm_wq);
+ spin_lock_init(&gdev->event_spinlock);
+ mutex_init(&gdev->session_mutex);
+ mutex_init(&gdev->cancel_req_mutex);
+ timer_setup(&gdev->heartbeat_timer, vbg_heartbeat_timer, 0);
+ INIT_WORK(&gdev->mem_balloon.work, vbg_balloon_work);
+
+ gdev->mem_balloon.get_req =
+ vbg_req_alloc(sizeof(*gdev->mem_balloon.get_req),
+ VMMDEVREQ_GET_MEMBALLOON_CHANGE_REQ,
+ VBG_KERNEL_REQUEST);
+ gdev->mem_balloon.change_req =
+ vbg_req_alloc(sizeof(*gdev->mem_balloon.change_req),
+ VMMDEVREQ_CHANGE_MEMBALLOON,
+ VBG_KERNEL_REQUEST);
+ gdev->cancel_req =
+ vbg_req_alloc(sizeof(*(gdev->cancel_req)),
+ VMMDEVREQ_HGCM_CANCEL2,
+ VBG_KERNEL_REQUEST);
+ gdev->ack_events_req =
+ vbg_req_alloc(sizeof(*gdev->ack_events_req),
+ VMMDEVREQ_ACKNOWLEDGE_EVENTS,
+ VBG_KERNEL_REQUEST);
+ gdev->mouse_status_req =
+ vbg_req_alloc(sizeof(*gdev->mouse_status_req),
+ VMMDEVREQ_GET_MOUSE_STATUS,
+ VBG_KERNEL_REQUEST);
+
+ if (!gdev->mem_balloon.get_req || !gdev->mem_balloon.change_req ||
+ !gdev->cancel_req || !gdev->ack_events_req ||
+ !gdev->mouse_status_req)
+ goto err_free_reqs;
+
+ ret = vbg_query_host_version(gdev);
+ if (ret)
+ goto err_free_reqs;
+
+ ret = vbg_report_guest_info(gdev);
+ if (ret) {
+ vbg_err("vboxguest: vbg_report_guest_info error: %d\n", ret);
+ goto err_free_reqs;
+ }
+
+ ret = vbg_reset_host_event_filter(gdev, gdev->fixed_events);
+ if (ret) {
+ vbg_err("vboxguest: Error setting fixed event filter: %d\n",
+ ret);
+ goto err_free_reqs;
+ }
+
+ ret = vbg_reset_host_capabilities(gdev);
+ if (ret) {
+ vbg_err("vboxguest: Error clearing guest capabilities: %d\n",
+ ret);
+ goto err_free_reqs;
+ }
+
+ ret = vbg_core_set_mouse_status(gdev, 0);
+ if (ret) {
+ vbg_err("vboxguest: Error clearing mouse status: %d\n", ret);
+ goto err_free_reqs;
+ }
+
+ /* These may fail without requiring the driver init to fail. */
+ vbg_guest_mappings_init(gdev);
+ vbg_heartbeat_init(gdev);
+
+ /* All Done! */
+ ret = vbg_report_driver_status(gdev, true);
+ if (ret < 0)
+ vbg_err("vboxguest: Error reporting driver status: %d\n", ret);
+
+ return 0;
+
+err_free_reqs:
+ vbg_req_free(gdev->mouse_status_req,
+ sizeof(*gdev->mouse_status_req));
+ vbg_req_free(gdev->ack_events_req,
+ sizeof(*gdev->ack_events_req));
+ vbg_req_free(gdev->cancel_req,
+ sizeof(*gdev->cancel_req));
+ vbg_req_free(gdev->mem_balloon.change_req,
+ sizeof(*gdev->mem_balloon.change_req));
+ vbg_req_free(gdev->mem_balloon.get_req,
+ sizeof(*gdev->mem_balloon.get_req));
+ return ret;
+}
+
+/**
+ * Call this on exit to clean-up vboxguest-core managed resources.
+ *
+ * The native code should call this before the driver is loaded,
+ * but don't call this on shutdown.
+ * @gdev: The Guest extension device.
+ */
+void vbg_core_exit(struct vbg_dev *gdev)
+{
+ vbg_heartbeat_exit(gdev);
+ vbg_guest_mappings_exit(gdev);
+
+ /* Clear the host flags (mouse status etc). */
+ vbg_reset_host_event_filter(gdev, 0);
+ vbg_reset_host_capabilities(gdev);
+ vbg_core_set_mouse_status(gdev, 0);
+
+ vbg_req_free(gdev->mouse_status_req,
+ sizeof(*gdev->mouse_status_req));
+ vbg_req_free(gdev->ack_events_req,
+ sizeof(*gdev->ack_events_req));
+ vbg_req_free(gdev->cancel_req,
+ sizeof(*gdev->cancel_req));
+ vbg_req_free(gdev->mem_balloon.change_req,
+ sizeof(*gdev->mem_balloon.change_req));
+ vbg_req_free(gdev->mem_balloon.get_req,
+ sizeof(*gdev->mem_balloon.get_req));
+}
+
+/**
+ * Creates a VBoxGuest user session.
+ *
+ * vboxguest_linux.c calls this when userspace opens the char-device.
+ * Return: A pointer to the new session or an ERR_PTR on error.
+ * @gdev: The Guest extension device.
+ * @requestor: VMMDEV_REQUESTOR_* flags
+ */
+struct vbg_session *vbg_core_open_session(struct vbg_dev *gdev, u32 requestor)
+{
+ struct vbg_session *session;
+
+ session = kzalloc(sizeof(*session), GFP_KERNEL);
+ if (!session)
+ return ERR_PTR(-ENOMEM);
+
+ session->gdev = gdev;
+ session->requestor = requestor;
+
+ return session;
+}
+
+/**
+ * Closes a VBoxGuest session.
+ * @session: The session to close (and free).
+ */
+void vbg_core_close_session(struct vbg_session *session)
+{
+ struct vbg_dev *gdev = session->gdev;
+ int i, rc;
+
+ vbg_acquire_session_capabilities(gdev, session, 0, U32_MAX, 0, true);
+ vbg_set_session_capabilities(gdev, session, 0, U32_MAX, true);
+ vbg_set_session_event_filter(gdev, session, 0, U32_MAX, true);
+
+ for (i = 0; i < ARRAY_SIZE(session->hgcm_client_ids); i++) {
+ if (!session->hgcm_client_ids[i])
+ continue;
+
+ /* requestor is kernel here, as we're cleaning up. */
+ vbg_hgcm_disconnect(gdev, VBG_KERNEL_REQUEST,
+ session->hgcm_client_ids[i], &rc);
+ }
+
+ kfree(session);
+}
+
+static int vbg_ioctl_chk(struct vbg_ioctl_hdr *hdr, size_t in_size,
+ size_t out_size)
+{
+ if (hdr->size_in != (sizeof(*hdr) + in_size) ||
+ hdr->size_out != (sizeof(*hdr) + out_size))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int vbg_ioctl_driver_version_info(
+ struct vbg_ioctl_driver_version_info *info)
+{
+ const u16 vbg_maj_version = VBG_IOC_VERSION >> 16;
+ u16 min_maj_version, req_maj_version;
+
+ if (vbg_ioctl_chk(&info->hdr, sizeof(info->u.in), sizeof(info->u.out)))
+ return -EINVAL;
+
+ req_maj_version = info->u.in.req_version >> 16;
+ min_maj_version = info->u.in.min_version >> 16;
+
+ if (info->u.in.min_version > info->u.in.req_version ||
+ min_maj_version != req_maj_version)
+ return -EINVAL;
+
+ if (info->u.in.min_version <= VBG_IOC_VERSION &&
+ min_maj_version == vbg_maj_version) {
+ info->u.out.session_version = VBG_IOC_VERSION;
+ } else {
+ info->u.out.session_version = U32_MAX;
+ info->hdr.rc = VERR_VERSION_MISMATCH;
+ }
+
+ info->u.out.driver_version = VBG_IOC_VERSION;
+ info->u.out.driver_revision = 0;
+ info->u.out.reserved1 = 0;
+ info->u.out.reserved2 = 0;
+
+ return 0;
+}
+
+/* Must be called with the event_lock held */
+static u32 vbg_get_allowed_event_mask_for_session(struct vbg_dev *gdev,
+ struct vbg_session *session)
+{
+ u32 acquire_mode_caps = gdev->acquire_mode_guest_caps;
+ u32 session_acquired_caps = session->acquired_guest_caps;
+ u32 allowed_events = VMMDEV_EVENT_VALID_EVENT_MASK;
+
+ if ((acquire_mode_caps & VMMDEV_GUEST_SUPPORTS_GRAPHICS) &&
+ !(session_acquired_caps & VMMDEV_GUEST_SUPPORTS_GRAPHICS))
+ allowed_events &= ~VMMDEV_EVENT_DISPLAY_CHANGE_REQUEST;
+
+ if ((acquire_mode_caps & VMMDEV_GUEST_SUPPORTS_SEAMLESS) &&
+ !(session_acquired_caps & VMMDEV_GUEST_SUPPORTS_SEAMLESS))
+ allowed_events &= ~VMMDEV_EVENT_SEAMLESS_MODE_CHANGE_REQUEST;
+
+ return allowed_events;
+}
+
+static bool vbg_wait_event_cond(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ u32 event_mask)
+{
+ unsigned long flags;
+ bool wakeup;
+ u32 events;
+
+ spin_lock_irqsave(&gdev->event_spinlock, flags);
+
+ events = gdev->pending_events & event_mask;
+ events &= vbg_get_allowed_event_mask_for_session(gdev, session);
+ wakeup = events || session->cancel_waiters;
+
+ spin_unlock_irqrestore(&gdev->event_spinlock, flags);
+
+ return wakeup;
+}
+
+/* Must be called with the event_lock held */
+static u32 vbg_consume_events_locked(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ u32 event_mask)
+{
+ u32 events = gdev->pending_events & event_mask;
+
+ events &= vbg_get_allowed_event_mask_for_session(gdev, session);
+ gdev->pending_events &= ~events;
+ return events;
+}
+
+static int vbg_ioctl_wait_for_events(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ struct vbg_ioctl_wait_for_events *wait)
+{
+ u32 timeout_ms = wait->u.in.timeout_ms;
+ u32 event_mask = wait->u.in.events;
+ unsigned long flags;
+ long timeout;
+ int ret = 0;
+
+ if (vbg_ioctl_chk(&wait->hdr, sizeof(wait->u.in), sizeof(wait->u.out)))
+ return -EINVAL;
+
+ if (timeout_ms == U32_MAX)
+ timeout = MAX_SCHEDULE_TIMEOUT;
+ else
+ timeout = msecs_to_jiffies(timeout_ms);
+
+ wait->u.out.events = 0;
+ do {
+ timeout = wait_event_interruptible_timeout(
+ gdev->event_wq,
+ vbg_wait_event_cond(gdev, session, event_mask),
+ timeout);
+
+ spin_lock_irqsave(&gdev->event_spinlock, flags);
+
+ if (timeout < 0 || session->cancel_waiters) {
+ ret = -EINTR;
+ } else if (timeout == 0) {
+ ret = -ETIMEDOUT;
+ } else {
+ wait->u.out.events =
+ vbg_consume_events_locked(gdev, session, event_mask);
+ }
+
+ spin_unlock_irqrestore(&gdev->event_spinlock, flags);
+
+ /*
+ * Someone else may have consumed the event(s) first, in
+ * which case we go back to waiting.
+ */
+ } while (ret == 0 && wait->u.out.events == 0);
+
+ return ret;
+}
+
+static int vbg_ioctl_interrupt_all_wait_events(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ struct vbg_ioctl_hdr *hdr)
+{
+ unsigned long flags;
+
+ if (hdr->size_in != sizeof(*hdr) || hdr->size_out != sizeof(*hdr))
+ return -EINVAL;
+
+ spin_lock_irqsave(&gdev->event_spinlock, flags);
+ session->cancel_waiters = true;
+ spin_unlock_irqrestore(&gdev->event_spinlock, flags);
+
+ wake_up(&gdev->event_wq);
+
+ return 0;
+}
+
+/**
+ * Checks if the VMM request is allowed in the context of the given session.
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @session: The calling session.
+ * @req: The request.
+ */
+static int vbg_req_allowed(struct vbg_dev *gdev, struct vbg_session *session,
+ const struct vmmdev_request_header *req)
+{
+ const struct vmmdev_guest_status *guest_status;
+ bool trusted_apps_only;
+
+ switch (req->request_type) {
+ /* Trusted users apps only. */
+ case VMMDEVREQ_QUERY_CREDENTIALS:
+ case VMMDEVREQ_REPORT_CREDENTIALS_JUDGEMENT:
+ case VMMDEVREQ_REGISTER_SHARED_MODULE:
+ case VMMDEVREQ_UNREGISTER_SHARED_MODULE:
+ case VMMDEVREQ_WRITE_COREDUMP:
+ case VMMDEVREQ_GET_CPU_HOTPLUG_REQ:
+ case VMMDEVREQ_SET_CPU_HOTPLUG_STATUS:
+ case VMMDEVREQ_CHECK_SHARED_MODULES:
+ case VMMDEVREQ_GET_PAGE_SHARING_STATUS:
+ case VMMDEVREQ_DEBUG_IS_PAGE_SHARED:
+ case VMMDEVREQ_REPORT_GUEST_STATS:
+ case VMMDEVREQ_REPORT_GUEST_USER_STATE:
+ case VMMDEVREQ_GET_STATISTICS_CHANGE_REQ:
+ trusted_apps_only = true;
+ break;
+
+ /* Anyone. */
+ case VMMDEVREQ_GET_MOUSE_STATUS:
+ case VMMDEVREQ_SET_MOUSE_STATUS:
+ case VMMDEVREQ_SET_POINTER_SHAPE:
+ case VMMDEVREQ_GET_HOST_VERSION:
+ case VMMDEVREQ_IDLE:
+ case VMMDEVREQ_GET_HOST_TIME:
+ case VMMDEVREQ_SET_POWER_STATUS:
+ case VMMDEVREQ_ACKNOWLEDGE_EVENTS:
+ case VMMDEVREQ_CTL_GUEST_FILTER_MASK:
+ case VMMDEVREQ_REPORT_GUEST_STATUS:
+ case VMMDEVREQ_GET_DISPLAY_CHANGE_REQ:
+ case VMMDEVREQ_VIDEMODE_SUPPORTED:
+ case VMMDEVREQ_GET_HEIGHT_REDUCTION:
+ case VMMDEVREQ_GET_DISPLAY_CHANGE_REQ2:
+ case VMMDEVREQ_VIDEMODE_SUPPORTED2:
+ case VMMDEVREQ_VIDEO_ACCEL_ENABLE:
+ case VMMDEVREQ_VIDEO_ACCEL_FLUSH:
+ case VMMDEVREQ_VIDEO_SET_VISIBLE_REGION:
+ case VMMDEVREQ_VIDEO_UPDATE_MONITOR_POSITIONS:
+ case VMMDEVREQ_GET_DISPLAY_CHANGE_REQEX:
+ case VMMDEVREQ_GET_DISPLAY_CHANGE_REQ_MULTI:
+ case VMMDEVREQ_GET_SEAMLESS_CHANGE_REQ:
+ case VMMDEVREQ_GET_VRDPCHANGE_REQ:
+ case VMMDEVREQ_LOG_STRING:
+ case VMMDEVREQ_GET_SESSION_ID:
+ trusted_apps_only = false;
+ break;
+
+ /* Depends on the request parameters... */
+ case VMMDEVREQ_REPORT_GUEST_CAPABILITIES:
+ guest_status = (const struct vmmdev_guest_status *)req;
+ switch (guest_status->facility) {
+ case VBOXGUEST_FACILITY_TYPE_ALL:
+ case VBOXGUEST_FACILITY_TYPE_VBOXGUEST_DRIVER:
+ vbg_err("Denying userspace vmm report guest cap. call facility %#08x\n",
+ guest_status->facility);
+ return -EPERM;
+ case VBOXGUEST_FACILITY_TYPE_VBOX_SERVICE:
+ trusted_apps_only = true;
+ break;
+ case VBOXGUEST_FACILITY_TYPE_VBOX_TRAY_CLIENT:
+ case VBOXGUEST_FACILITY_TYPE_SEAMLESS:
+ case VBOXGUEST_FACILITY_TYPE_GRAPHICS:
+ default:
+ trusted_apps_only = false;
+ break;
+ }
+ break;
+
+ /* Anything else is not allowed. */
+ default:
+ vbg_err("Denying userspace vmm call type %#08x\n",
+ req->request_type);
+ return -EPERM;
+ }
+
+ if (trusted_apps_only &&
+ (session->requestor & VMMDEV_REQUESTOR_USER_DEVICE)) {
+ vbg_err("Denying userspace vmm call type %#08x through vboxuser device node\n",
+ req->request_type);
+ return -EPERM;
+ }
+
+ return 0;
+}
+
+static int vbg_ioctl_vmmrequest(struct vbg_dev *gdev,
+ struct vbg_session *session, void *data)
+{
+ struct vbg_ioctl_hdr *hdr = data;
+ int ret;
+
+ if (hdr->size_in != hdr->size_out)
+ return -EINVAL;
+
+ if (hdr->size_in > VMMDEV_MAX_VMMDEVREQ_SIZE)
+ return -E2BIG;
+
+ if (hdr->type == VBG_IOCTL_HDR_TYPE_DEFAULT)
+ return -EINVAL;
+
+ ret = vbg_req_allowed(gdev, session, data);
+ if (ret < 0)
+ return ret;
+
+ vbg_req_perform(gdev, data);
+ WARN_ON(hdr->rc == VINF_HGCM_ASYNC_EXECUTE);
+
+ return 0;
+}
+
+static int vbg_ioctl_hgcm_connect(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ struct vbg_ioctl_hgcm_connect *conn)
+{
+ u32 client_id;
+ int i, ret;
+
+ if (vbg_ioctl_chk(&conn->hdr, sizeof(conn->u.in), sizeof(conn->u.out)))
+ return -EINVAL;
+
+ /* Find a free place in the sessions clients array and claim it */
+ mutex_lock(&gdev->session_mutex);
+ for (i = 0; i < ARRAY_SIZE(session->hgcm_client_ids); i++) {
+ if (!session->hgcm_client_ids[i]) {
+ session->hgcm_client_ids[i] = U32_MAX;
+ break;
+ }
+ }
+ mutex_unlock(&gdev->session_mutex);
+
+ if (i >= ARRAY_SIZE(session->hgcm_client_ids))
+ return -EMFILE;
+
+ ret = vbg_hgcm_connect(gdev, session->requestor, &conn->u.in.loc,
+ &client_id, &conn->hdr.rc);
+
+ mutex_lock(&gdev->session_mutex);
+ if (ret == 0 && conn->hdr.rc >= 0) {
+ conn->u.out.client_id = client_id;
+ session->hgcm_client_ids[i] = client_id;
+ } else {
+ conn->u.out.client_id = 0;
+ session->hgcm_client_ids[i] = 0;
+ }
+ mutex_unlock(&gdev->session_mutex);
+
+ return ret;
+}
+
+static int vbg_ioctl_hgcm_disconnect(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ struct vbg_ioctl_hgcm_disconnect *disconn)
+{
+ u32 client_id;
+ int i, ret;
+
+ if (vbg_ioctl_chk(&disconn->hdr, sizeof(disconn->u.in), 0))
+ return -EINVAL;
+
+ client_id = disconn->u.in.client_id;
+ if (client_id == 0 || client_id == U32_MAX)
+ return -EINVAL;
+
+ mutex_lock(&gdev->session_mutex);
+ for (i = 0; i < ARRAY_SIZE(session->hgcm_client_ids); i++) {
+ if (session->hgcm_client_ids[i] == client_id) {
+ session->hgcm_client_ids[i] = U32_MAX;
+ break;
+ }
+ }
+ mutex_unlock(&gdev->session_mutex);
+
+ if (i >= ARRAY_SIZE(session->hgcm_client_ids))
+ return -EINVAL;
+
+ ret = vbg_hgcm_disconnect(gdev, session->requestor, client_id,
+ &disconn->hdr.rc);
+
+ mutex_lock(&gdev->session_mutex);
+ if (ret == 0 && disconn->hdr.rc >= 0)
+ session->hgcm_client_ids[i] = 0;
+ else
+ session->hgcm_client_ids[i] = client_id;
+ mutex_unlock(&gdev->session_mutex);
+
+ return ret;
+}
+
+static bool vbg_param_valid(enum vmmdev_hgcm_function_parameter_type type)
+{
+ switch (type) {
+ case VMMDEV_HGCM_PARM_TYPE_32BIT:
+ case VMMDEV_HGCM_PARM_TYPE_64BIT:
+ case VMMDEV_HGCM_PARM_TYPE_LINADDR:
+ case VMMDEV_HGCM_PARM_TYPE_LINADDR_IN:
+ case VMMDEV_HGCM_PARM_TYPE_LINADDR_OUT:
+ return true;
+ default:
+ return false;
+ }
+}
+
+static int vbg_ioctl_hgcm_call(struct vbg_dev *gdev,
+ struct vbg_session *session, bool f32bit,
+ struct vbg_ioctl_hgcm_call *call)
+{
+ size_t actual_size;
+ u32 client_id;
+ int i, ret;
+
+ if (call->hdr.size_in < sizeof(*call))
+ return -EINVAL;
+
+ if (call->hdr.size_in != call->hdr.size_out)
+ return -EINVAL;
+
+ if (call->parm_count > VMMDEV_HGCM_MAX_PARMS)
+ return -E2BIG;
+
+ client_id = call->client_id;
+ if (client_id == 0 || client_id == U32_MAX)
+ return -EINVAL;
+
+ actual_size = sizeof(*call);
+ if (f32bit)
+ actual_size += call->parm_count *
+ sizeof(struct vmmdev_hgcm_function_parameter32);
+ else
+ actual_size += call->parm_count *
+ sizeof(struct vmmdev_hgcm_function_parameter);
+ if (call->hdr.size_in < actual_size) {
+ vbg_debug("VBG_IOCTL_HGCM_CALL: hdr.size_in %d required size is %zd\n",
+ call->hdr.size_in, actual_size);
+ return -EINVAL;
+ }
+ call->hdr.size_out = actual_size;
+
+ /* Validate parameter types */
+ if (f32bit) {
+ struct vmmdev_hgcm_function_parameter32 *parm =
+ VBG_IOCTL_HGCM_CALL_PARMS32(call);
+
+ for (i = 0; i < call->parm_count; i++)
+ if (!vbg_param_valid(parm[i].type))
+ return -EINVAL;
+ } else {
+ struct vmmdev_hgcm_function_parameter *parm =
+ VBG_IOCTL_HGCM_CALL_PARMS(call);
+
+ for (i = 0; i < call->parm_count; i++)
+ if (!vbg_param_valid(parm[i].type))
+ return -EINVAL;
+ }
+
+ /*
+ * Validate the client id.
+ */
+ mutex_lock(&gdev->session_mutex);
+ for (i = 0; i < ARRAY_SIZE(session->hgcm_client_ids); i++)
+ if (session->hgcm_client_ids[i] == client_id)
+ break;
+ mutex_unlock(&gdev->session_mutex);
+ if (i >= ARRAY_SIZE(session->hgcm_client_ids)) {
+ vbg_debug("VBG_IOCTL_HGCM_CALL: INVALID handle. u32Client=%#08x\n",
+ client_id);
+ return -EINVAL;
+ }
+
+ if (IS_ENABLED(CONFIG_COMPAT) && f32bit)
+ ret = vbg_hgcm_call32(gdev, session->requestor, client_id,
+ call->function, call->timeout_ms,
+ VBG_IOCTL_HGCM_CALL_PARMS32(call),
+ call->parm_count, &call->hdr.rc);
+ else
+ ret = vbg_hgcm_call(gdev, session->requestor, client_id,
+ call->function, call->timeout_ms,
+ VBG_IOCTL_HGCM_CALL_PARMS(call),
+ call->parm_count, &call->hdr.rc);
+
+ if (ret == -E2BIG) {
+ /* E2BIG needs to be reported through the hdr.rc field. */
+ call->hdr.rc = VERR_OUT_OF_RANGE;
+ ret = 0;
+ }
+
+ if (ret && ret != -EINTR && ret != -ETIMEDOUT)
+ vbg_err("VBG_IOCTL_HGCM_CALL error: %d\n", ret);
+
+ return ret;
+}
+
+static int vbg_ioctl_log(struct vbg_ioctl_log *log)
+{
+ if (log->hdr.size_out != sizeof(log->hdr))
+ return -EINVAL;
+
+ vbg_info("%.*s", (int)(log->hdr.size_in - sizeof(log->hdr)),
+ log->u.in.msg);
+
+ return 0;
+}
+
+static int vbg_ioctl_change_filter_mask(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ struct vbg_ioctl_change_filter *filter)
+{
+ u32 or_mask, not_mask;
+
+ if (vbg_ioctl_chk(&filter->hdr, sizeof(filter->u.in), 0))
+ return -EINVAL;
+
+ or_mask = filter->u.in.or_mask;
+ not_mask = filter->u.in.not_mask;
+
+ if ((or_mask | not_mask) & ~VMMDEV_EVENT_VALID_EVENT_MASK)
+ return -EINVAL;
+
+ return vbg_set_session_event_filter(gdev, session, or_mask, not_mask,
+ false);
+}
+
+static int vbg_ioctl_acquire_guest_capabilities(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ struct vbg_ioctl_acquire_guest_caps *caps)
+{
+ u32 flags, or_mask, not_mask;
+
+ if (vbg_ioctl_chk(&caps->hdr, sizeof(caps->u.in), 0))
+ return -EINVAL;
+
+ flags = caps->u.in.flags;
+ or_mask = caps->u.in.or_mask;
+ not_mask = caps->u.in.not_mask;
+
+ if (flags & ~VBGL_IOC_AGC_FLAGS_VALID_MASK)
+ return -EINVAL;
+
+ if ((or_mask | not_mask) & ~VMMDEV_GUEST_CAPABILITIES_MASK)
+ return -EINVAL;
+
+ return vbg_acquire_session_capabilities(gdev, session, or_mask,
+ not_mask, flags, false);
+}
+
+static int vbg_ioctl_change_guest_capabilities(struct vbg_dev *gdev,
+ struct vbg_session *session, struct vbg_ioctl_set_guest_caps *caps)
+{
+ u32 or_mask, not_mask;
+ int ret;
+
+ if (vbg_ioctl_chk(&caps->hdr, sizeof(caps->u.in), sizeof(caps->u.out)))
+ return -EINVAL;
+
+ or_mask = caps->u.in.or_mask;
+ not_mask = caps->u.in.not_mask;
+
+ if ((or_mask | not_mask) & ~VMMDEV_GUEST_CAPABILITIES_MASK)
+ return -EINVAL;
+
+ ret = vbg_set_session_capabilities(gdev, session, or_mask, not_mask,
+ false);
+ if (ret)
+ return ret;
+
+ caps->u.out.session_caps = session->set_guest_caps;
+ caps->u.out.global_caps = gdev->guest_caps_host;
+
+ return 0;
+}
+
+static int vbg_ioctl_check_balloon(struct vbg_dev *gdev,
+ struct vbg_ioctl_check_balloon *balloon_info)
+{
+ if (vbg_ioctl_chk(&balloon_info->hdr, 0, sizeof(balloon_info->u.out)))
+ return -EINVAL;
+
+ balloon_info->u.out.balloon_chunks = gdev->mem_balloon.chunks;
+ /*
+ * Under Linux we handle VMMDEV_EVENT_BALLOON_CHANGE_REQUEST
+ * events entirely in the kernel, see vbg_core_isr().
+ */
+ balloon_info->u.out.handle_in_r3 = false;
+
+ return 0;
+}
+
+static int vbg_ioctl_write_core_dump(struct vbg_dev *gdev,
+ struct vbg_session *session,
+ struct vbg_ioctl_write_coredump *dump)
+{
+ struct vmmdev_write_core_dump *req;
+
+ if (vbg_ioctl_chk(&dump->hdr, sizeof(dump->u.in), 0))
+ return -EINVAL;
+
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_WRITE_COREDUMP,
+ session->requestor);
+ if (!req)
+ return -ENOMEM;
+
+ req->flags = dump->u.in.flags;
+ dump->hdr.rc = vbg_req_perform(gdev, req);
+
+ vbg_req_free(req, sizeof(*req));
+ return 0;
+}
+
+/**
+ * Common IOCtl for user to kernel communication.
+ * Return: 0 or negative errno value.
+ * @session: The client session.
+ * @req: The requested function.
+ * @data: The i/o data buffer, minimum size sizeof(struct vbg_ioctl_hdr).
+ */
+int vbg_core_ioctl(struct vbg_session *session, unsigned int req, void *data)
+{
+ unsigned int req_no_size = req & ~IOCSIZE_MASK;
+ struct vbg_dev *gdev = session->gdev;
+ struct vbg_ioctl_hdr *hdr = data;
+ bool f32bit = false;
+
+ hdr->rc = VINF_SUCCESS;
+ if (!hdr->size_out)
+ hdr->size_out = hdr->size_in;
+
+ /*
+ * hdr->version and hdr->size_in / hdr->size_out minimum size are
+ * already checked by vbg_misc_device_ioctl().
+ */
+
+ /* For VMMDEV_REQUEST hdr->type != VBG_IOCTL_HDR_TYPE_DEFAULT */
+ if (req_no_size == VBG_IOCTL_VMMDEV_REQUEST(0) ||
+ req == VBG_IOCTL_VMMDEV_REQUEST_BIG ||
+ req == VBG_IOCTL_VMMDEV_REQUEST_BIG_ALT)
+ return vbg_ioctl_vmmrequest(gdev, session, data);
+
+ if (hdr->type != VBG_IOCTL_HDR_TYPE_DEFAULT)
+ return -EINVAL;
+
+ /* Fixed size requests. */
+ switch (req) {
+ case VBG_IOCTL_DRIVER_VERSION_INFO:
+ return vbg_ioctl_driver_version_info(data);
+ case VBG_IOCTL_HGCM_CONNECT:
+ return vbg_ioctl_hgcm_connect(gdev, session, data);
+ case VBG_IOCTL_HGCM_DISCONNECT:
+ return vbg_ioctl_hgcm_disconnect(gdev, session, data);
+ case VBG_IOCTL_WAIT_FOR_EVENTS:
+ return vbg_ioctl_wait_for_events(gdev, session, data);
+ case VBG_IOCTL_INTERRUPT_ALL_WAIT_FOR_EVENTS:
+ return vbg_ioctl_interrupt_all_wait_events(gdev, session, data);
+ case VBG_IOCTL_CHANGE_FILTER_MASK:
+ return vbg_ioctl_change_filter_mask(gdev, session, data);
+ case VBG_IOCTL_ACQUIRE_GUEST_CAPABILITIES:
+ return vbg_ioctl_acquire_guest_capabilities(gdev, session, data);
+ case VBG_IOCTL_CHANGE_GUEST_CAPABILITIES:
+ return vbg_ioctl_change_guest_capabilities(gdev, session, data);
+ case VBG_IOCTL_CHECK_BALLOON:
+ return vbg_ioctl_check_balloon(gdev, data);
+ case VBG_IOCTL_WRITE_CORE_DUMP:
+ return vbg_ioctl_write_core_dump(gdev, session, data);
+ }
+
+ /* Variable sized requests. */
+ switch (req_no_size) {
+#ifdef CONFIG_COMPAT
+ case VBG_IOCTL_HGCM_CALL_32(0):
+ f32bit = true;
+ fallthrough;
+#endif
+ case VBG_IOCTL_HGCM_CALL(0):
+ return vbg_ioctl_hgcm_call(gdev, session, f32bit, data);
+ case VBG_IOCTL_LOG(0):
+ case VBG_IOCTL_LOG_ALT(0):
+ return vbg_ioctl_log(data);
+ }
+
+ vbg_err_ratelimited("Userspace made an unknown ioctl req %#08x\n", req);
+ return -ENOTTY;
+}
+
+/**
+ * Report guest supported mouse-features to the host.
+ *
+ * Return: 0 or negative errno value.
+ * @gdev: The Guest extension device.
+ * @features: The set of features to report to the host.
+ */
+int vbg_core_set_mouse_status(struct vbg_dev *gdev, u32 features)
+{
+ struct vmmdev_mouse_status *req;
+ int rc;
+
+ req = vbg_req_alloc(sizeof(*req), VMMDEVREQ_SET_MOUSE_STATUS,
+ VBG_KERNEL_REQUEST);
+ if (!req)
+ return -ENOMEM;
+
+ req->mouse_features = features;
+ req->pointer_pos_x = 0;
+ req->pointer_pos_y = 0;
+
+ rc = vbg_req_perform(gdev, req);
+ if (rc < 0)
+ vbg_err("%s error, rc: %d\n", __func__, rc);
+
+ vbg_req_free(req, sizeof(*req));
+ return vbg_status_code_to_errno(rc);
+}
+
+/** Core interrupt service routine. */
+irqreturn_t vbg_core_isr(int irq, void *dev_id)
+{
+ struct vbg_dev *gdev = dev_id;
+ struct vmmdev_events *req = gdev->ack_events_req;
+ bool mouse_position_changed = false;
+ unsigned long flags;
+ u32 events = 0;
+ int rc;
+
+ if (!gdev->mmio->V.V1_04.have_events)
+ return IRQ_NONE;
+
+ /* Get and acknowlegde events. */
+ req->header.rc = VERR_INTERNAL_ERROR;
+ req->events = 0;
+ rc = vbg_req_perform(gdev, req);
+ if (rc < 0) {
+ vbg_err("Error performing events req, rc: %d\n", rc);
+ return IRQ_NONE;
+ }
+
+ events = req->events;
+
+ if (events & VMMDEV_EVENT_MOUSE_POSITION_CHANGED) {
+ mouse_position_changed = true;
+ events &= ~VMMDEV_EVENT_MOUSE_POSITION_CHANGED;
+ }
+
+ if (events & VMMDEV_EVENT_HGCM) {
+ wake_up(&gdev->hgcm_wq);
+ events &= ~VMMDEV_EVENT_HGCM;
+ }
+
+ if (events & VMMDEV_EVENT_BALLOON_CHANGE_REQUEST) {
+ schedule_work(&gdev->mem_balloon.work);
+ events &= ~VMMDEV_EVENT_BALLOON_CHANGE_REQUEST;
+ }
+
+ if (events) {
+ spin_lock_irqsave(&gdev->event_spinlock, flags);
+ gdev->pending_events |= events;
+ spin_unlock_irqrestore(&gdev->event_spinlock, flags);
+
+ wake_up(&gdev->event_wq);
+ }
+
+ if (mouse_position_changed)
+ vbg_linux_mouse_event(gdev);
+
+ return IRQ_HANDLED;
+}
diff --git a/drivers/virt/vboxguest/vboxguest_core.h b/drivers/virt/vboxguest/vboxguest_core.h
new file mode 100644
index 000000000..ab4bf64e2
--- /dev/null
+++ b/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
diff --git a/drivers/virt/vboxguest/vboxguest_linux.c b/drivers/virt/vboxguest/vboxguest_linux.c
new file mode 100644
index 000000000..c47e62dc5
--- /dev/null
+++ b/drivers/virt/vboxguest/vboxguest_linux.c
@@ -0,0 +1,500 @@
+/* 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;
+}
+
+/**
+ * Close device.
+ * Return: 0 on success, negated errno on failure.
+ * @inode: Pointer to inode info structure.
+ * @filp: Associated file pointer.
+ */
+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;
+}
+
+/**
+ * Device I/O Control entry point.
+ * Return: 0 on success, negated errno on failure.
+ * @filp: Associated file pointer.
+ * @req: The request specified to ioctl().
+ * @arg: The argument specified to ioctl().
+ */
+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");
diff --git a/drivers/virt/vboxguest/vboxguest_utils.c b/drivers/virt/vboxguest/vboxguest_utils.c
new file mode 100644
index 000000000..8d195e3f8
--- /dev/null
+++ b/drivers/virt/vboxguest/vboxguest_utils.c
@@ -0,0 +1,825 @@
+/* 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;
+}
+
+/**
+ * Preprocesses the HGCM call, validate parameters, alloc bounce buffers and
+ * figure out how much extra storage we need for page lists.
+ * Return: 0 or negative errno value.
+ * @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.
+ */
+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;
+}
+
+/**
+ * Translates linear address types to page list direction flags.
+ *
+ * Return: page list flags.
+ * @type: The type.
+ */
+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]);
+}
+
+/**
+ * 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;
+ }
+ }
+}
+
+/**
+ * Tries to cancel a pending HGCM call.
+ *
+ * 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;
+}
+
+/**
+ * Performs the call and completion wait.
+ * Return: 0 or negative errno value.
+ * @gdev: The VBoxGuest device extension.
+ * @call: The call to execute.
+ * @timeout_ms: Timeout in ms.
+ * @leak_it: Where to return the leak it / free it, indicator.
+ * Cancellation fun.
+ */
+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;
+}
+
+/**
+ * Copies the result of the call back to the caller info structure and user
+ * buffers.
+ * Return: 0 or negative errno value.
+ * @call: HGCM call request.
+ * @dst_parm: Pointer to function call parameters destination.
+ * @parm_count: Number of function call parameters.
+ * @bounce_bufs: The bouncebuffer array.
+ */
+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);
diff --git a/drivers/virt/vboxguest/vboxguest_version.h b/drivers/virt/vboxguest/vboxguest_version.h
new file mode 100644
index 000000000..84834dad3
--- /dev/null
+++ b/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
diff --git a/drivers/virt/vboxguest/vmmdev.h b/drivers/virt/vboxguest/vmmdev.h
new file mode 100644
index 000000000..21f408120
--- /dev/null
+++ b/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
diff --git a/drivers/virt/vmgenid.c b/drivers/virt/vmgenid.c
new file mode 100644
index 000000000..a1c467a0e
--- /dev/null
+++ b/drivers/virt/vmgenid.c
@@ -0,0 +1,101 @@
+// 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 and changes when a
+ * virtual machine forks or is cloned. This driver exists for shepherding that
+ * information to random.c.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/acpi.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 int vmgenid_add(struct acpi_device *device)
+{
+ struct acpi_buffer parsed = { ACPI_ALLOCATE_BUFFER };
+ struct vmgenid_state *state;
+ union acpi_object *obj;
+ phys_addr_t phys_addr;
+ acpi_status status;
+ int ret = 0;
+
+ state = devm_kmalloc(&device->dev, sizeof(*state), GFP_KERNEL);
+ if (!state)
+ return -ENOMEM;
+
+ 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);
+ state->next_id = devm_memremap(&device->dev, phys_addr, VMGENID_SIZE, MEMREMAP_WB);
+ if (IS_ERR(state->next_id)) {
+ ret = PTR_ERR(state->next_id);
+ goto out;
+ }
+
+ memcpy(state->this_id, state->next_id, sizeof(state->this_id));
+ add_device_randomness(state->this_id, sizeof(state->this_id));
+
+ device->driver_data = state;
+
+out:
+ ACPI_FREE(parsed.pointer);
+ return ret;
+}
+
+static void vmgenid_notify(struct acpi_device *device, u32 event)
+{
+ struct vmgenid_state *state = acpi_driver_data(device);
+ 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 const struct acpi_device_id vmgenid_ids[] = {
+ { "VMGENCTR", 0 },
+ { "VM_GEN_COUNTER", 0 },
+ { }
+};
+
+static struct acpi_driver vmgenid_driver = {
+ .name = "vmgenid",
+ .ids = vmgenid_ids,
+ .owner = THIS_MODULE,
+ .ops = {
+ .add = vmgenid_add,
+ .notify = vmgenid_notify
+ }
+};
+
+module_acpi_driver(vmgenid_driver);
+
+MODULE_DEVICE_TABLE(acpi, vmgenid_ids);
+MODULE_DESCRIPTION("Virtual Machine Generation ID");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");