*/
#include "qemu/osdep.h"
+#include "qapi/error.h"
#include "hw/sysbus.h"
#include "hw/arm/arm.h"
#include "hw/arm/primecell.h"
#include "net/net.h"
#include "sysemu/block-backend.h"
#include "sysemu/device_tree.h"
+#include "sysemu/numa.h"
#include "sysemu/sysemu.h"
#include "sysemu/kvm.h"
#include "hw/boards.h"
uint32_t clock_phandle;
uint32_t gic_phandle;
uint32_t v2m_phandle;
+ bool using_psci;
} VirtBoardInfo;
typedef struct {
#define VIRT_MACHINE_CLASS(klass) \
OBJECT_CLASS_CHECK(VirtMachineClass, klass, TYPE_VIRT_MACHINE)
+/* RAM limit in GB. Since VIRT_MEM starts at the 1GB mark, this means
+ * RAM can go up to the 256GB mark, leaving 256GB of the physical
+ * address space unallocated and free for future use between 256G and 512G.
+ * If we need to provide more RAM to VMs in the future then we need to:
+ * * allocate a second bank of RAM starting at 2TB and working up
+ * * fix the DT and ACPI table generation code in QEMU to correctly
+ * report two split lumps of RAM to the guest
+ * * fix KVM in the host kernel to allow guests with >40 bit address spaces
+ * (We don't want to fill all the way up to 512GB with RAM because
+ * we might want it for non-RAM purposes later. Conversely it seems
+ * reasonable to assume that anybody configuring a VM with a quarter
+ * of a terabyte of RAM will be doing it on a host with more than a
+ * terabyte of physical address space.)
+ */
+#define RAMLIMIT_GB 255
+#define RAMLIMIT_BYTES (RAMLIMIT_GB * 1024ULL * 1024 * 1024)
+
/* Addresses and sizes of our components.
* 0..128MB is space for a flash device so we can run bootrom code such as UEFI.
* 128MB..256MB is used for miscellaneous device I/O.
[VIRT_MMIO] = { 0x0a000000, 0x00000200 },
/* ...repeating for a total of NUM_VIRTIO_TRANSPORTS, each of that size */
[VIRT_PLATFORM_BUS] = { 0x0c000000, 0x02000000 },
+ [VIRT_SECURE_MEM] = { 0x0e000000, 0x01000000 },
[VIRT_PCIE_MMIO] = { 0x10000000, 0x2eff0000 },
[VIRT_PCIE_PIO] = { 0x3eff0000, 0x00010000 },
[VIRT_PCIE_ECAM] = { 0x3f000000, 0x01000000 },
- [VIRT_MEM] = { 0x40000000, 30ULL * 1024 * 1024 * 1024 },
+ [VIRT_MEM] = { 0x40000000, RAMLIMIT_BYTES },
/* Second PCIe window, 512GB wide at the 512GB boundary */
[VIRT_PCIE_MMIO_HIGH] = { 0x8000000000ULL, 0x8000000000ULL },
};
void *fdt = vbi->fdt;
ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(0));
+ if (!vbi->using_psci) {
+ return;
+ }
+
qemu_fdt_add_subnode(fdt, "/psci");
if (armcpu->psci_version == 2) {
const char comp[] = "arm,psci-0.2\0arm,psci";
{
int cpu;
int addr_cells = 1;
+ unsigned int i;
/*
* From Documentation/devicetree/bindings/arm/cpus.txt
qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible",
armcpu->dtb_compatible);
- if (vbi->smp_cpus > 1) {
+ if (vbi->using_psci && vbi->smp_cpus > 1) {
qemu_fdt_setprop_string(vbi->fdt, nodename,
"enable-method", "psci");
}
armcpu->mp_affinity);
}
+ for (i = 0; i < nb_numa_nodes; i++) {
+ if (test_bit(cpu, numa_info[i].node_cpu)) {
+ qemu_fdt_setprop_cell(vbi->fdt, nodename, "numa-node-id", i);
+ }
+ }
+
g_free(nodename);
}
}
qemu_fdt_setprop_cell(vbi->fdt, "/intc", "phandle", vbi->gic_phandle);
}
+static void fdt_add_pmu_nodes(const VirtBoardInfo *vbi, int gictype)
+{
+ CPUState *cpu;
+ ARMCPU *armcpu;
+ uint32_t irqflags = GIC_FDT_IRQ_FLAGS_LEVEL_HI;
+
+ CPU_FOREACH(cpu) {
+ armcpu = ARM_CPU(cpu);
+ if (!armcpu->has_pmu ||
+ !kvm_arm_pmu_create(cpu, PPI(VIRTUAL_PMU_IRQ))) {
+ return;
+ }
+ }
+
+ if (gictype == 2) {
+ irqflags = deposit32(irqflags, GIC_FDT_IRQ_PPI_CPU_START,
+ GIC_FDT_IRQ_PPI_CPU_WIDTH,
+ (1 << vbi->smp_cpus) - 1);
+ }
+
+ armcpu = ARM_CPU(qemu_get_cpu(0));
+ qemu_fdt_add_subnode(vbi->fdt, "/pmu");
+ if (arm_feature(&armcpu->env, ARM_FEATURE_V8)) {
+ const char compat[] = "arm,armv8-pmuv3";
+ qemu_fdt_setprop(vbi->fdt, "/pmu", "compatible",
+ compat, sizeof(compat));
+ qemu_fdt_setprop_cells(vbi->fdt, "/pmu", "interrupts",
+ GIC_FDT_IRQ_TYPE_PPI, VIRTUAL_PMU_IRQ, irqflags);
+ }
+}
+
static void create_v2m(VirtBoardInfo *vbi, qemu_irq *pic)
{
int i;
}
static void create_uart(const VirtBoardInfo *vbi, qemu_irq *pic, int uart,
- MemoryRegion *mem)
+ MemoryRegion *mem, CharDriverState *chr)
{
char *nodename;
hwaddr base = vbi->memmap[uart].base;
DeviceState *dev = qdev_create(NULL, "pl011");
SysBusDevice *s = SYS_BUS_DEVICE(dev);
+ qdev_prop_set_chr(dev, "chardev", chr);
qdev_init_nofail(dev);
memory_region_add_subregion(mem, base,
sysbus_mmio_get_region(s, 0));
g_free(nodename);
}
-static DeviceState *pl061_dev;
+static DeviceState *gpio_key_dev;
static void virt_powerdown_req(Notifier *n, void *opaque)
{
/* use gpio Pin 3 for power button event */
- qemu_set_irq(qdev_get_gpio_in(pl061_dev, 3), 1);
+ qemu_set_irq(qdev_get_gpio_in(gpio_key_dev, 0), 1);
}
static Notifier virt_system_powerdown_notifier = {
static void create_gpio(const VirtBoardInfo *vbi, qemu_irq *pic)
{
char *nodename;
+ DeviceState *pl061_dev;
hwaddr base = vbi->memmap[VIRT_GPIO].base;
hwaddr size = vbi->memmap[VIRT_GPIO].size;
int irq = vbi->irqmap[VIRT_GPIO];
qemu_fdt_setprop_string(vbi->fdt, nodename, "clock-names", "apb_pclk");
qemu_fdt_setprop_cell(vbi->fdt, nodename, "phandle", phandle);
+ gpio_key_dev = sysbus_create_simple("gpio-key", -1,
+ qdev_get_gpio_in(pl061_dev, 3));
qemu_fdt_add_subnode(vbi->fdt, "/gpio-keys");
qemu_fdt_setprop_string(vbi->fdt, "/gpio-keys", "compatible", "gpio-keys");
qemu_fdt_setprop_cell(vbi->fdt, "/gpio-keys", "#size-cells", 0);
}
static void create_one_flash(const char *name, hwaddr flashbase,
- hwaddr flashsize)
+ hwaddr flashsize, const char *file,
+ MemoryRegion *sysmem)
{
/* Create and map a single flash device. We use the same
* parameters as the flash devices on the Versatile Express board.
*/
DriveInfo *dinfo = drive_get_next(IF_PFLASH);
DeviceState *dev = qdev_create(NULL, "cfi.pflash01");
+ SysBusDevice *sbd = SYS_BUS_DEVICE(dev);
const uint64_t sectorlength = 256 * 1024;
if (dinfo) {
qdev_prop_set_string(dev, "name", name);
qdev_init_nofail(dev);
- sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, flashbase);
-}
+ memory_region_add_subregion(sysmem, flashbase,
+ sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0));
-static void create_flash(const VirtBoardInfo *vbi)
-{
- /* Create two flash devices to fill the VIRT_FLASH space in the memmap.
- * Any file passed via -bios goes in the first of these.
- */
- hwaddr flashsize = vbi->memmap[VIRT_FLASH].size / 2;
- hwaddr flashbase = vbi->memmap[VIRT_FLASH].base;
- char *nodename;
-
- if (bios_name) {
+ if (file) {
char *fn;
int image_size;
"but you cannot use both options at once");
exit(1);
}
- fn = qemu_find_file(QEMU_FILE_TYPE_BIOS, bios_name);
+ fn = qemu_find_file(QEMU_FILE_TYPE_BIOS, file);
if (!fn) {
- error_report("Could not find ROM image '%s'", bios_name);
+ error_report("Could not find ROM image '%s'", file);
exit(1);
}
- image_size = load_image_targphys(fn, flashbase, flashsize);
+ image_size = load_image_mr(fn, sysbus_mmio_get_region(sbd, 0));
g_free(fn);
if (image_size < 0) {
- error_report("Could not load ROM image '%s'", bios_name);
+ error_report("Could not load ROM image '%s'", file);
exit(1);
}
}
+}
+
+static void create_flash(const VirtBoardInfo *vbi,
+ MemoryRegion *sysmem,
+ MemoryRegion *secure_sysmem)
+{
+ /* Create two flash devices to fill the VIRT_FLASH space in the memmap.
+ * Any file passed via -bios goes in the first of these.
+ * sysmem is the system memory space. secure_sysmem is the secure view
+ * of the system, and the first flash device should be made visible only
+ * there. The second flash device is visible to both secure and nonsecure.
+ * If sysmem == secure_sysmem this means there is no separate Secure
+ * address space and both flash devices are generally visible.
+ */
+ hwaddr flashsize = vbi->memmap[VIRT_FLASH].size / 2;
+ hwaddr flashbase = vbi->memmap[VIRT_FLASH].base;
+ char *nodename;
- create_one_flash("virt.flash0", flashbase, flashsize);
- create_one_flash("virt.flash1", flashbase + flashsize, flashsize);
+ create_one_flash("virt.flash0", flashbase, flashsize,
+ bios_name, secure_sysmem);
+ create_one_flash("virt.flash1", flashbase + flashsize, flashsize,
+ NULL, sysmem);
- nodename = g_strdup_printf("/flash@%" PRIx64, flashbase);
- qemu_fdt_add_subnode(vbi->fdt, nodename);
- qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", "cfi-flash");
- qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg",
- 2, flashbase, 2, flashsize,
- 2, flashbase + flashsize, 2, flashsize);
- qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4);
- g_free(nodename);
+ if (sysmem == secure_sysmem) {
+ /* Report both flash devices as a single node in the DT */
+ nodename = g_strdup_printf("/flash@%" PRIx64, flashbase);
+ qemu_fdt_add_subnode(vbi->fdt, nodename);
+ qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", "cfi-flash");
+ qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg",
+ 2, flashbase, 2, flashsize,
+ 2, flashbase + flashsize, 2, flashsize);
+ qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4);
+ g_free(nodename);
+ } else {
+ /* Report the devices as separate nodes so we can mark one as
+ * only visible to the secure world.
+ */
+ nodename = g_strdup_printf("/secflash@%" PRIx64, flashbase);
+ qemu_fdt_add_subnode(vbi->fdt, nodename);
+ qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", "cfi-flash");
+ qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg",
+ 2, flashbase, 2, flashsize);
+ qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4);
+ qemu_fdt_setprop_string(vbi->fdt, nodename, "status", "disabled");
+ qemu_fdt_setprop_string(vbi->fdt, nodename, "secure-status", "okay");
+ g_free(nodename);
+
+ nodename = g_strdup_printf("/flash@%" PRIx64, flashbase);
+ qemu_fdt_add_subnode(vbi->fdt, nodename);
+ qemu_fdt_setprop_string(vbi->fdt, nodename, "compatible", "cfi-flash");
+ qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg",
+ 2, flashbase + flashsize, 2, flashsize);
+ qemu_fdt_setprop_cell(vbi->fdt, nodename, "bank-width", 4);
+ g_free(nodename);
+ }
}
static void create_fw_cfg(const VirtBoardInfo *vbi, AddressSpace *as)
sysbus_mmio_get_region(s, 0));
}
+static void create_secure_ram(VirtBoardInfo *vbi, MemoryRegion *secure_sysmem)
+{
+ MemoryRegion *secram = g_new(MemoryRegion, 1);
+ char *nodename;
+ hwaddr base = vbi->memmap[VIRT_SECURE_MEM].base;
+ hwaddr size = vbi->memmap[VIRT_SECURE_MEM].size;
+
+ memory_region_init_ram(secram, NULL, "virt.secure-ram", size, &error_fatal);
+ vmstate_register_ram_global(secram);
+ memory_region_add_subregion(secure_sysmem, base, secram);
+
+ nodename = g_strdup_printf("/secram@%" PRIx64, base);
+ qemu_fdt_add_subnode(vbi->fdt, nodename);
+ qemu_fdt_setprop_string(vbi->fdt, nodename, "device_type", "memory");
+ qemu_fdt_setprop_sized_cells(vbi->fdt, nodename, "reg", 2, base, 2, size);
+ qemu_fdt_setprop_string(vbi->fdt, nodename, "status", "disabled");
+ qemu_fdt_setprop_string(vbi->fdt, nodename, "secure-status", "okay");
+
+ g_free(nodename);
+}
+
static void *machvirt_dtb(const struct arm_boot_info *binfo, int *fdt_size)
{
const VirtBoardInfo *board = (const VirtBoardInfo *)binfo;
MemoryRegion *sysmem = get_system_memory();
MemoryRegion *secure_sysmem = NULL;
int gic_version = vms->gic_version;
- int n, max_cpus;
+ int n, virt_max_cpus;
MemoryRegion *ram = g_new(MemoryRegion, 1);
const char *cpu_model = machine->cpu_model;
VirtBoardInfo *vbi;
VirtGuestInfoState *guest_info_state = g_malloc0(sizeof *guest_info_state);
VirtGuestInfo *guest_info = &guest_info_state->info;
char **cpustr;
+ bool firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0);
if (!cpu_model) {
cpu_model = "cortex-a15";
* KVM is not available yet
*/
if (!gic_version) {
+ if (!kvm_enabled()) {
+ error_report("gic-version=host requires KVM");
+ exit(1);
+ }
+
gic_version = kvm_arm_vgic_probe();
if (!gic_version) {
error_report("Unable to determine GIC version supported by host");
- error_printf("KVM acceleration is probably not supported\n");
exit(1);
}
}
exit(1);
}
+ /* If we have an EL3 boot ROM then the assumption is that it will
+ * implement PSCI itself, so disable QEMU's internal implementation
+ * so it doesn't get in the way. Instead of starting secondary
+ * CPUs in PSCI powerdown state we will start them all running and
+ * let the boot ROM sort them out.
+ * The usual case is that we do use QEMU's PSCI implementation.
+ */
+ vbi->using_psci = !(vms->secure && firmware_loaded);
+
/* The maximum number of CPUs depends on the GIC version, or on how
* many redistributors we can fit into the memory map.
*/
if (gic_version == 3) {
- max_cpus = vbi->memmap[VIRT_GIC_REDIST].size / 0x20000;
+ virt_max_cpus = vbi->memmap[VIRT_GIC_REDIST].size / 0x20000;
} else {
- max_cpus = GIC_NCPU;
+ virt_max_cpus = GIC_NCPU;
}
- if (smp_cpus > max_cpus) {
+ if (max_cpus > virt_max_cpus) {
error_report("Number of SMP CPUs requested (%d) exceeds max CPUs "
"supported by machine 'mach-virt' (%d)",
- smp_cpus, max_cpus);
+ max_cpus, virt_max_cpus);
exit(1);
}
vbi->smp_cpus = smp_cpus;
if (machine->ram_size > vbi->memmap[VIRT_MEM].size) {
- error_report("mach-virt: cannot model more than 30GB RAM");
+ error_report("mach-virt: cannot model more than %dGB RAM", RAMLIMIT_GB);
exit(1);
}
object_property_set_bool(cpuobj, false, "has_el3", NULL);
}
- object_property_set_int(cpuobj, QEMU_PSCI_CONDUIT_HVC, "psci-conduit",
- NULL);
+ if (vbi->using_psci) {
+ object_property_set_int(cpuobj, QEMU_PSCI_CONDUIT_HVC,
+ "psci-conduit", NULL);
- /* Secondary CPUs start in PSCI powered-down state */
- if (n > 0) {
- object_property_set_bool(cpuobj, true, "start-powered-off", NULL);
+ /* Secondary CPUs start in PSCI powered-down state */
+ if (n > 0) {
+ object_property_set_bool(cpuobj, true,
+ "start-powered-off", NULL);
+ }
}
if (object_property_find(cpuobj, "reset-cbar", NULL)) {
machine->ram_size);
memory_region_add_subregion(sysmem, vbi->memmap[VIRT_MEM].base, ram);
- create_flash(vbi);
+ create_flash(vbi, sysmem, secure_sysmem ? secure_sysmem : sysmem);
create_gic(vbi, pic, gic_version, vms->secure);
- create_uart(vbi, pic, VIRT_UART, sysmem);
+ fdt_add_pmu_nodes(vbi, gic_version);
+
+ create_uart(vbi, pic, VIRT_UART, sysmem, serial_hds[0]);
if (vms->secure) {
- create_uart(vbi, pic, VIRT_SECURE_UART, secure_sysmem);
+ create_secure_ram(vbi, secure_sysmem);
+ create_uart(vbi, pic, VIRT_SECURE_UART, secure_sysmem, serial_hds[1]);
}
create_rtc(vbi, pic);
vbi->bootinfo.board_id = -1;
vbi->bootinfo.loader_start = vbi->memmap[VIRT_MEM].base;
vbi->bootinfo.get_dtb = machvirt_dtb;
- vbi->bootinfo.firmware_loaded = bios_name || drive_get(IF_PFLASH, 0, 0);
+ vbi->bootinfo.firmware_loaded = firmware_loaded;
arm_load_kernel(ARM_CPU(first_cpu), &vbi->bootinfo);
/*
}
}
-static void virt_instance_init(Object *obj)
+static void virt_machine_class_init(ObjectClass *oc, void *data)
+{
+ MachineClass *mc = MACHINE_CLASS(oc);
+
+ mc->init = machvirt_init;
+ /* Start max_cpus at the maximum QEMU supports. We'll further restrict
+ * it later in machvirt_init, where we have more information about the
+ * configuration of the particular instance.
+ */
+ mc->max_cpus = MAX_CPUMASK_BITS;
+ mc->has_dynamic_sysbus = true;
+ mc->block_default_type = IF_VIRTIO;
+ mc->no_cdrom = 1;
+ mc->pci_allow_0_address = true;
+}
+
+static const TypeInfo virt_machine_info = {
+ .name = TYPE_VIRT_MACHINE,
+ .parent = TYPE_MACHINE,
+ .abstract = true,
+ .instance_size = sizeof(VirtMachineState),
+ .class_size = sizeof(VirtMachineClass),
+ .class_init = virt_machine_class_init,
+};
+
+static void machvirt_machine_init(void)
+{
+ type_register_static(&virt_machine_info);
+}
+type_init(machvirt_machine_init);
+
+static void virt_2_6_instance_init(Object *obj)
{
VirtMachineState *vms = VIRT_MACHINE(obj);
"Valid values are 2, 3 and host", NULL);
}
-static void virt_class_init(ObjectClass *oc, void *data)
+static void virt_2_6_class_init(ObjectClass *oc, void *data)
{
MachineClass *mc = MACHINE_CLASS(oc);
- mc->desc = "ARM Virtual Machine",
- mc->init = machvirt_init;
- /* Start max_cpus at the maximum QEMU supports. We'll further restrict
- * it later in machvirt_init, where we have more information about the
- * configuration of the particular instance.
- */
- mc->max_cpus = MAX_CPUMASK_BITS;
- mc->has_dynamic_sysbus = true;
- mc->block_default_type = IF_VIRTIO;
- mc->no_cdrom = 1;
- mc->pci_allow_0_address = true;
+ mc->desc = "QEMU 2.6 ARM Virtual Machine";
+ mc->alias = "virt";
}
-static const TypeInfo machvirt_info = {
- .name = TYPE_VIRT_MACHINE,
- .parent = TYPE_MACHINE,
- .instance_size = sizeof(VirtMachineState),
- .instance_init = virt_instance_init,
- .class_size = sizeof(VirtMachineClass),
- .class_init = virt_class_init,
+static const TypeInfo machvirt_2_6_info = {
+ .name = MACHINE_TYPE_NAME("virt-2.6"),
+ .parent = TYPE_VIRT_MACHINE,
+ .instance_init = virt_2_6_instance_init,
+ .class_init = virt_2_6_class_init,
};
-static void machvirt_machine_init(void)
+static void machvirt_machine_2_6_init(void)
{
- type_register_static(&machvirt_info);
+ type_register_static(&machvirt_2_6_info);
}
-
-machine_init(machvirt_machine_init);
+type_init(machvirt_machine_2_6_init);