New files to add HAX support

QEMU emulator interacts with the HAX kernel module. A HAX (Hardware-based Accelerated eXecution)
kernel module is required to use HAX support. Most guest instructions run in VMX non-root
(i.e. in hardware) mode and achieve near-native (relative to the host) performance.
QEMU still emulates PIO/MMIO instructions and non-PG (paging) mode operations.

HAX is supported only on Mac OS X and Windows hosts when Intel VT is present.

Change-Id: I8dd52a35e315437dc568f555742bb8ab7e9d8ab2
Signed-off-by: Zhang, Xiantao <xiantao.zhang@intel.com>
Signed-off-by: Xin, Xiaohui <xiaohui.xin@intel.com>
Signed-off-by: Jiang Yunhong <yunhong.jiang@intel.com>
Signed-off-by: Nakajima, Jun <jun.nakajima@intel.com>

1 files changed, 466 insertions, 0 deletions

diff --git a/target-i386/hax-windows.c b/target-i386/hax-windows.c
new file mode 100644
index 0000000..683a227
--- /dev/null
+++ b/target-i386/hax-windows.c
@@ -0,0 +1,466 @@
+/*
+** Copyright (c) 2011, Intel Corporation
+**
+** This software is licensed under the terms of the GNU General Public
+** License version 2, as published by the Free Software Foundation, and
+** may be copied, distributed, and modified under those terms.
+**
+** This program is distributed in the hope that it will be useful,
+** but WITHOUT ANY WARRANTY; without even the implied warranty of
+** MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+** GNU General Public License for more details.
+*/
+
+#include "target-i386/hax-i386.h"
+
+/*
+ * return 0 upon success, -1 when the driver is not loaded,
+ * other negative value for other failures
+ */
+static int hax_open_device(hax_fd *fd)
+{
+    uint32_t errNum = 0;
+    HANDLE hDevice;
+
+    if (!fd)
+        return -2;
+
+    hDevice = CreateFile( "\\\\.\\HAX",
+      GENERIC_READ | GENERIC_WRITE,
+      0,
+      NULL,
+      CREATE_ALWAYS,
+      FILE_ATTRIBUTE_NORMAL,
+      NULL);
+
+    if (hDevice == INVALID_HANDLE_VALUE)
+    {
+        dprint("Failed to open the HAX device!\n");
+        errNum = GetLastError();
+        if (errNum == ERROR_FILE_NOT_FOUND)
+            return -1;
+        return -2;
+    }
+    *fd = hDevice;
+    dprint("device fd:%d\n", *fd);
+    return 0;
+}
+
+
+hax_fd hax_mod_open(void)
+{
+    int ret;
+    hax_fd fd;
+
+    ret = hax_open_device(&fd);
+    if (ret != 0)
+        dprint("Open HAX device failed\n");
+
+    return fd;
+}
+
+int hax_populate_ram(uint64_t va, uint32_t size)
+{
+    int ret;
+    struct hax_alloc_ram_info info;
+    HANDLE hDeviceVM;
+    DWORD dSize = 0;
+
+    if (!hax_global.vm || !hax_global.vm->fd)
+    {
+        dprint("Allocate memory before vm create?\n");
+        return -EINVAL;
+    }
+
+    info.size = size;
+    info.va = va;
+
+    hDeviceVM = hax_global.vm->fd;
+
+    ret = DeviceIoControl(hDeviceVM,
+      HAX_VM_IOCTL_ALLOC_RAM,
+      &info, sizeof(info),
+      NULL, 0,
+      &dSize,
+      (LPOVERLAPPED) NULL);
+
+    if (!ret) {
+        dprint("Failed to allocate %x memory\n", size);
+        return ret;
+    }
+
+    return 0;
+}
+
+
+int hax_set_phys_mem(target_phys_addr_t start_addr, ram_addr_t size, ram_addr_t phys_offset)
+{
+    struct hax_set_ram_info info, *pinfo = &info;
+    ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK;
+    HANDLE hDeviceVM;
+    DWORD dSize = 0;
+    int ret = 0;
+
+    /* We look for the  RAM and ROM only */
+    if (flags >= IO_MEM_UNASSIGNED)
+        return 0;
+
+    if ( (start_addr & ~TARGET_PAGE_MASK) || (size & ~TARGET_PAGE_MASK))
+    {
+        dprint(
+          "set_phys_mem %x %lx requires page aligned addr and size\n",
+          start_addr, size);
+        return -1;
+    }
+
+    info.pa_start = start_addr;
+    info.size = size;
+    info.va = (uint64_t)qemu_get_ram_ptr(phys_offset);
+    info.flags = (flags & IO_MEM_ROM) ? 1 : 0;
+
+    hDeviceVM = hax_global.vm->fd;
+
+    ret = DeviceIoControl(hDeviceVM,
+      HAX_VM_IOCTL_SET_RAM,
+      pinfo, sizeof(*pinfo),
+      NULL, 0,
+      &dSize,
+      (LPOVERLAPPED) NULL);
+
+    if (!ret)
+        return -EFAULT;
+    else
+        return 0;
+}
+
+int hax_mod_version(struct hax_state *hax, struct hax_module_version *version)
+{
+    int ret;
+    HANDLE hDevice = hax->fd;   //handle to hax module
+    DWORD dSize = 0;
+    DWORD err = 0;
+
+    if (hax_invalid_fd(hDevice)) {
+        dprint("Invalid fd for hax device!\n");
+        return -ENODEV;
+    }
+
+    ret = DeviceIoControl(hDevice,
+      HAX_IOCTL_VERSION,
+      NULL, 0,
+      version, sizeof(*version),
+      &dSize,
+      (LPOVERLAPPED) NULL);
+
+    if (!ret) {
+        err = GetLastError();
+        if (err == ERROR_INSUFFICIENT_BUFFER ||
+            err == ERROR_MORE_DATA)
+            dprint("HAX module is too large.\n");
+        dprint("Failed to get Hax module version:%d\n", err);
+        return -EFAULT;
+    } else
+        return 0;
+}
+
+static char *hax_vm_devfs_string(int vm_id)
+{
+    char *name;
+
+    if (vm_id > MAX_VM_ID)
+    {
+        dprint("Too big VM id\n");
+        return NULL;
+    }
+
+    name = qemu_strdup("\\\\.\\hax_vmxx");
+    if (!name)
+        return NULL;
+    sprintf(name, "\\\\.\\hax_vm%02d", vm_id);
+
+    return name;
+}
+
+static char *hax_vcpu_devfs_string(int vm_id, int vcpu_id)
+{
+    char *name;
+
+    if (vm_id > MAX_VM_ID || vcpu_id > MAX_VCPU_ID)
+    {
+        dprint("Too big vm id %x or vcpu id %x\n", vm_id, vcpu_id);
+        return NULL;
+    }
+    name = qemu_strdup("\\\\.\\hax_vmxx_vcpuxx");
+    if (!name)
+        return NULL;
+    sprintf(name, "\\\\.\\hax_vm%02d_vcpu%02d", vm_id, vcpu_id);
+
+    return name;
+}
+
+int hax_host_create_vm(struct hax_state *hax, int vm_id)
+{
+    int ret;
+    DWORD dSize = 0;
+
+    if (hax_invalid_fd(hax->fd))
+        return -EINVAL;
+
+    if (hax->vm)
+        return 0;
+
+    ret = DeviceIoControl(hax->fd,
+      HAX_IOCTL_CREATE_VM,
+      NULL, 0,
+      &vm_id, sizeof(vm_id),
+      &dSize,
+      (LPOVERLAPPED) NULL);
+    if (!ret) {
+        dprint("error code:%d", GetLastError());
+        return -1;
+    }
+
+    return 0;
+}
+
+hax_fd hax_host_open_vm(struct hax_state *hax, int vm_id)
+{
+    char *vm_name = NULL;
+    hax_fd hDeviceVM;
+
+    vm_name = hax_vm_devfs_string(vm_id);
+    if (!vm_name) {
+        dprint("Incorrect name\n");
+        return INVALID_HANDLE_VALUE;
+    }
+
+    hDeviceVM = CreateFile(vm_name,
+      GENERIC_READ | GENERIC_WRITE,
+      0,
+      NULL,
+      CREATE_ALWAYS,
+      FILE_ATTRIBUTE_NORMAL,
+      NULL);
+    if (hDeviceVM == INVALID_HANDLE_VALUE)
+        dprint("Open the vm devcie error:%s, ec:%d\n", vm_name, GetLastError());
+
+    qemu_free(vm_name);
+    return hDeviceVM;
+}
+
+int hax_host_create_vcpu(hax_fd vm_fd, int vcpuid)
+{
+    int ret;
+    DWORD dSize = 0;
+
+    ret = DeviceIoControl(vm_fd,
+      HAX_VM_IOCTL_VCPU_CREATE,
+      &vcpuid, sizeof(vcpuid),
+      NULL, 0,
+      &dSize,
+      (LPOVERLAPPED) NULL);
+    if (!ret)
+    {
+        dprint("Failed to create vcpu %x\n", vcpuid);
+        return -1;
+    }
+
+    return 0;
+}
+
+hax_fd hax_host_open_vcpu(int vmid, int vcpuid)
+{
+    char *devfs_path = NULL;
+    hax_fd hDeviceVCPU;
+
+    devfs_path = hax_vcpu_devfs_string(vmid, vcpuid);
+    if (!devfs_path)
+    {
+        dprint("Failed to get the devfs\n");
+        return INVALID_HANDLE_VALUE;
+    }
+
+    hDeviceVCPU = CreateFile( devfs_path,
+      GENERIC_READ | GENERIC_WRITE,
+      0,
+      NULL,
+      CREATE_ALWAYS,
+      FILE_ATTRIBUTE_NORMAL,
+      NULL);
+
+    if (hDeviceVCPU == INVALID_HANDLE_VALUE)
+        dprint("Failed to open the vcpu devfs\n");
+    qemu_free(devfs_path);
+    return hDeviceVCPU;
+}
+
+int hax_host_setup_vcpu_channel(struct hax_vcpu_state *vcpu)
+{
+    hax_fd hDeviceVCPU = vcpu->fd;
+    int ret;
+    struct hax_tunnel_info info;
+    DWORD dSize = 0;
+
+    ret = DeviceIoControl(hDeviceVCPU,
+      HAX_VCPU_IOCTL_SETUP_TUNNEL,
+      NULL, 0,
+      &info, sizeof(info),
+      &dSize,
+      (LPOVERLAPPED) NULL);
+    if (!ret)
+    {
+        dprint("Failed to setup the hax tunnel\n");
+        return -1;
+    }
+
+    if (!valid_hax_tunnel_size(info.size))
+    {
+        dprint("Invalid hax tunnel size %x\n", info.size);
+        ret = -EINVAL;
+        return ret;
+    }
+    vcpu->tunnel = (struct hax_tunnel *)(info.va);
+    vcpu->iobuf = (unsigned char *)(info.io_va);
+    return 0;
+}
+
+int hax_vcpu_run(struct hax_vcpu_state* vcpu)
+{
+    int ret;
+    HANDLE hDeviceVCPU = vcpu->fd;
+    DWORD dSize = 0;
+
+    ret = DeviceIoControl(hDeviceVCPU,
+      HAX_VCPU_IOCTL_RUN,
+      NULL, 0,
+      NULL, 0,
+      &dSize,
+      (LPOVERLAPPED) NULL);
+    if (!ret)
+        return -EFAULT;
+    else
+        return 0;
+}
+
+int hax_sync_fpu(CPUState *env, struct fx_layout *fl, int set)
+{
+    int ret;
+    hax_fd fd;
+    HANDLE hDeviceVCPU;
+    DWORD dSize = 0;
+
+    fd = hax_vcpu_get_fd(env);
+    if (hax_invalid_fd(fd))
+        return -1;
+
+    hDeviceVCPU = fd;
+
+    if (set)
+        ret = DeviceIoControl(hDeviceVCPU,
+          HAX_VCPU_IOCTL_SET_FPU,
+          fl, sizeof(*fl),
+          NULL, 0,
+          &dSize,
+          (LPOVERLAPPED) NULL);
+    else
+        ret = DeviceIoControl(hDeviceVCPU,
+          HAX_VCPU_IOCTL_GET_FPU,
+          NULL, 0,
+          fl, sizeof(*fl),
+          &dSize,
+          (LPOVERLAPPED) NULL);
+    if (!ret)
+        return -EFAULT;
+    else
+        return 0;
+}
+
+int hax_sync_msr(CPUState *env, struct hax_msr_data *msrs, int set)
+{
+    int ret;
+    hax_fd fd;
+    HANDLE hDeviceVCPU;
+    DWORD dSize = 0;
+
+    fd = hax_vcpu_get_fd(env);
+    if (hax_invalid_fd(fd))
+        return -1;
+    hDeviceVCPU = fd;
+
+    if (set)
+        ret = DeviceIoControl(hDeviceVCPU,
+          HAX_VCPU_IOCTL_SET_MSRS,
+          msrs, sizeof(*msrs),
+          msrs, sizeof(*msrs),
+          &dSize,
+          (LPOVERLAPPED) NULL);
+    else
+        ret = DeviceIoControl(hDeviceVCPU,
+          HAX_VCPU_IOCTL_GET_MSRS,
+          msrs, sizeof(*msrs),
+          msrs, sizeof(*msrs),
+          &dSize,
+          (LPOVERLAPPED) NULL);
+    if (!ret)
+        return -EFAULT;
+    else
+        return 0;
+}
+
+int hax_sync_vcpu_state(CPUState *env, struct vcpu_state_t *state, int set)
+{
+    int ret;
+    hax_fd fd;
+    HANDLE hDeviceVCPU;
+    DWORD dSize;
+
+    fd = hax_vcpu_get_fd(env);
+    if (hax_invalid_fd(fd))
+        return -1;
+
+    hDeviceVCPU = fd;
+
+    if (set)
+        ret = DeviceIoControl(hDeviceVCPU,
+          HAX_VCPU_SET_REGS,
+          state, sizeof(*state),
+          NULL, 0,
+          &dSize,
+          (LPOVERLAPPED) NULL);
+    else
+        ret = DeviceIoControl(hDeviceVCPU,
+          HAX_VCPU_GET_REGS,
+          NULL, 0,
+          state, sizeof(*state),
+          &dSize,
+          (LPOVERLAPPED) NULL);
+    if (!ret)
+        return -EFAULT;
+    else
+        return 0;
+}
+
+int hax_inject_interrupt(CPUState *env, int vector)
+{
+    int ret;
+    hax_fd fd;
+    HANDLE hDeviceVCPU;
+    DWORD dSize;
+
+    fd = hax_vcpu_get_fd(env);
+    if (hax_invalid_fd(fd))
+        return -1;
+
+    hDeviceVCPU = fd;
+
+    ret = DeviceIoControl(hDeviceVCPU,
+      HAX_VCPU_IOCTL_INTERRUPT,
+      &vector, sizeof(vector),
+      NULL, 0,
+      &dSize,
+      (LPOVERLAPPED) NULL);
+    if (!ret)
+        return -EFAULT;
+    else
+        return 0;
+}