#include "kvm/kvm.h"
+#include "kvm/cpufeature.h"
+#include "kvm/interrupt.h"
+#include "kvm/boot-protocol.h"
+#include "kvm/util.h"
+#include "kvm/mptable.h"
+
#include <linux/kvm.h>
#include <asm/bootparam.h>
#include <sys/ioctl.h>
-#include <inttypes.h>
#include <sys/mman.h>
+#include <sys/stat.h>
#include <stdbool.h>
+#include <assert.h>
#include <limits.h>
+#include <signal.h>
#include <stdarg.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <stdio.h>
#include <fcntl.h>
-
-#include "util.h"
-
-/*
- * Compatibility code. Remove this when we move to tools/kvm.
- */
-#ifndef KVM_EXIT_INTERNAL_ERROR
-# define KVM_EXIT_INTERNAL_ERROR 17
-#endif
+#include <time.h>
#define DEFINE_KVM_EXIT_REASON(reason) [reason] = #reason
DEFINE_KVM_EXIT_REASON(KVM_EXIT_INTERNAL_ERROR),
};
-static inline uint32_t segment_to_flat(uint16_t selector, uint16_t offset)
-{
- return ((uint32_t)selector << 4) + (uint32_t) offset;
-}
+#define DEFINE_KVM_EXT(ext) \
+ .name = #ext, \
+ .code = ext
+
+struct {
+ const char *name;
+ int code;
+} kvm_req_ext[] = {
+ { DEFINE_KVM_EXT(KVM_CAP_COALESCED_MMIO) },
+ { DEFINE_KVM_EXT(KVM_CAP_SET_TSS_ADDR) },
+ { DEFINE_KVM_EXT(KVM_CAP_PIT2) },
+ { DEFINE_KVM_EXT(KVM_CAP_USER_MEMORY) },
+ { DEFINE_KVM_EXT(KVM_CAP_IRQ_ROUTING) },
+ { DEFINE_KVM_EXT(KVM_CAP_IRQCHIP) },
+ { DEFINE_KVM_EXT(KVM_CAP_HLT) },
+ { DEFINE_KVM_EXT(KVM_CAP_IRQ_INJECT_STATUS) },
+ { DEFINE_KVM_EXT(KVM_CAP_EXT_CPUID) },
+};
-static inline void *guest_flat_to_host(struct kvm *self, unsigned long offset)
+static bool kvm__supports_extension(struct kvm *kvm, unsigned int extension)
{
- return self->ram_start + offset;
-}
+ int ret;
-static inline void *guest_real_to_host(struct kvm *self, uint16_t selector, uint16_t offset)
-{
- unsigned long flat = segment_to_flat(selector, offset);
+ ret = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, extension);
+ if (ret < 0)
+ return false;
- return guest_flat_to_host(self, flat);
+ return ret;
}
-static bool kvm__supports_extension(struct kvm *self, unsigned int extension)
+static int kvm__check_extensions(struct kvm *kvm)
{
- int ret;
+ unsigned int i;
- ret = ioctl(self->sys_fd, KVM_CHECK_EXTENSION, extension);
- if (ret < 0)
- return false;
+ for (i = 0; i < ARRAY_SIZE(kvm_req_ext); i++) {
+ if (!kvm__supports_extension(kvm, kvm_req_ext[i].code)) {
+ pr_error("Unsuppored KVM extension detected: %s",
+ kvm_req_ext[i].name);
+ return (int)-i;
+ }
+ }
- return ret;
+ return 0;
}
static struct kvm *kvm__new(void)
{
- struct kvm *self = calloc(1, sizeof *self);
+ struct kvm *kvm = calloc(1, sizeof *kvm);
- if (!self)
+ if (!kvm)
die("out of memory");
- return self;
+ return kvm;
}
-struct kvm *kvm__init(void)
+void kvm__delete(struct kvm *kvm)
{
- struct kvm_userspace_memory_region mem;
- struct kvm *self;
- long page_size;
- int mmap_size;
- int ret;
+ kvm__stop_timer(kvm);
- self = kvm__new();
+ munmap(kvm->ram_start, kvm->ram_size);
+ free(kvm);
+}
- self->sys_fd = open("/dev/kvm", O_RDWR);
- if (self->sys_fd < 0)
- die_perror("open");
+static bool kvm__cpu_supports_vm(void)
+{
+ struct cpuid_regs regs;
+ u32 eax_base;
+ int feature;
- ret = ioctl(self->sys_fd, KVM_GET_API_VERSION, 0);
- if (ret != KVM_API_VERSION)
- die_perror("KVM_API_VERSION ioctl");
+ regs = (struct cpuid_regs) {
+ .eax = 0x00,
+ };
+ host_cpuid(®s);
- self->vm_fd = ioctl(self->sys_fd, KVM_CREATE_VM, 0);
- if (self->vm_fd < 0)
- die_perror("KVM_CREATE_VM ioctl");
+ switch (regs.ebx) {
+ case CPUID_VENDOR_INTEL_1:
+ eax_base = 0x00;
+ feature = KVM__X86_FEATURE_VMX;
+ break;
- if (!kvm__supports_extension(self, KVM_CAP_USER_MEMORY))
- die("KVM_CAP_USER_MEMORY is not supported");
+ case CPUID_VENDOR_AMD_1:
+ eax_base = 0x80000000;
+ feature = KVM__X86_FEATURE_SVM;
+ break;
- self->ram_size = 64UL * 1024UL * 1024UL;
+ default:
+ return false;
+ }
- page_size = sysconf(_SC_PAGESIZE);
- if (posix_memalign(&self->ram_start, page_size, self->ram_size) != 0)
- die("out of memory");
+ regs = (struct cpuid_regs) {
+ .eax = eax_base,
+ };
+ host_cpuid(®s);
+
+ if (regs.eax < eax_base + 0x01)
+ return false;
+
+ regs = (struct cpuid_regs) {
+ .eax = eax_base + 0x01
+ };
+ host_cpuid(®s);
+
+ return regs.ecx & (1 << feature);
+}
+
+static void kvm_register_mem_slot(struct kvm *kvm, u32 slot, u64 guest_phys, u64 size, void *userspace_addr)
+{
+ struct kvm_userspace_memory_region mem;
+ int ret;
mem = (struct kvm_userspace_memory_region) {
- .slot = 0,
- .guest_phys_addr = 0x0UL,
- .memory_size = self->ram_size,
- .userspace_addr = (unsigned long) self->ram_start,
+ .slot = slot,
+ .guest_phys_addr = guest_phys,
+ .memory_size = size,
+ .userspace_addr = (unsigned long)userspace_addr,
};
- ret = ioctl(self->vm_fd, KVM_SET_USER_MEMORY_REGION, &mem, 1);
+ ret = ioctl(kvm->vm_fd, KVM_SET_USER_MEMORY_REGION, &mem);
if (ret < 0)
die_perror("KVM_SET_USER_MEMORY_REGION ioctl");
+}
- if (!kvm__supports_extension(self, KVM_CAP_SET_TSS_ADDR))
- die("KVM_CAP_SET_TSS_ADDR is not supported");
+/*
+ * Allocating RAM size bigger than 4GB requires us to leave a gap
+ * in the RAM which is used for PCI MMIO, hotplug, and unconfigured
+ * devices (see documentation of e820_setup_gap() for details).
+ *
+ * If we're required to initialize RAM bigger than 4GB, we will create
+ * a gap between 0xe0000000 and 0x100000000 in the guest virtual mem space.
+ */
- ret = ioctl(self->vm_fd, KVM_SET_TSS_ADDR, 0xfffbd000);
- if (ret < 0)
- die_perror("KVM_SET_TSS_ADDR ioctl");
+void kvm__init_ram(struct kvm *kvm)
+{
+ u64 phys_start, phys_size;
+ void *host_mem;
+
+ if (kvm->ram_size < KVM_32BIT_GAP_START) {
+ /* Use a single block of RAM for 32bit RAM */
+
+ phys_start = 0;
+ phys_size = kvm->ram_size;
+ host_mem = kvm->ram_start;
+
+ kvm_register_mem_slot(kvm, 0, 0, kvm->ram_size, kvm->ram_start);
+ } else {
+ /* First RAM range from zero to the PCI gap: */
+
+ phys_start = 0;
+ phys_size = KVM_32BIT_GAP_START;
+ host_mem = kvm->ram_start;
- self->vcpu_fd = ioctl(self->vm_fd, KVM_CREATE_VCPU, 0);
- if (self->vcpu_fd < 0)
- die_perror("KVM_CREATE_VCPU ioctl");
+ kvm_register_mem_slot(kvm, 0, phys_start, phys_size, host_mem);
- mmap_size = ioctl(self->sys_fd, KVM_GET_VCPU_MMAP_SIZE, 0);
- if (mmap_size < 0)
- die_perror("KVM_GET_VCPU_MMAP_SIZE ioctl");
+ /* Second RAM range from 4GB to the end of RAM: */
- self->kvm_run = mmap(NULL, mmap_size, PROT_READ|PROT_WRITE, MAP_SHARED, self->vcpu_fd, 0);
- if (self->kvm_run == MAP_FAILED)
- die("unable to mmap vcpu fd");
+ phys_start = 0x100000000ULL;
+ phys_size = kvm->ram_size - phys_size;
+ host_mem = kvm->ram_start + phys_start;
- return self;
+ kvm_register_mem_slot(kvm, 1, phys_start, phys_size, host_mem);
+ }
}
-void kvm__enable_singlestep(struct kvm *self)
+int kvm__max_cpus(struct kvm *kvm)
{
- struct kvm_guest_debug debug = {
- .control = KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_SINGLESTEP,
- };
+ int ret;
+
+ ret = ioctl(kvm->sys_fd, KVM_CHECK_EXTENSION, KVM_CAP_NR_VCPUS);
+ if (ret < 0)
+ die_perror("KVM_CAP_NR_VCPUS");
+
+ return ret;
+}
+
+struct kvm *kvm__init(const char *kvm_dev, unsigned long ram_size)
+{
+ struct kvm_pit_config pit_config = { .flags = 0, };
+ struct kvm *kvm;
+ int ret;
+
+ if (!kvm__cpu_supports_vm())
+ die("Your CPU does not support hardware virtualization");
+
+ kvm = kvm__new();
+
+ kvm->sys_fd = open(kvm_dev, O_RDWR);
+ if (kvm->sys_fd < 0) {
+ if (errno == ENOENT)
+ die("'%s' not found. Please make sure your kernel has CONFIG_KVM enabled and that the KVM modules are loaded.", kvm_dev);
+ if (errno == ENODEV)
+ die("'%s' KVM driver not available.\n # (If the KVM module is loaded then 'dmesg' may offer further clues about the failure.)", kvm_dev);
+
+ fprintf(stderr, " Fatal, could not open %s: ", kvm_dev);
+ perror(NULL);
+ exit(1);
+ }
+
+ ret = ioctl(kvm->sys_fd, KVM_GET_API_VERSION, 0);
+ if (ret != KVM_API_VERSION)
+ die_perror("KVM_API_VERSION ioctl");
+
+ kvm->vm_fd = ioctl(kvm->sys_fd, KVM_CREATE_VM, 0);
+ if (kvm->vm_fd < 0)
+ die_perror("KVM_CREATE_VM ioctl");
+
+ if (kvm__check_extensions(kvm))
+ die("A required KVM extention is not supported by OS");
- if (ioctl(self->vcpu_fd, KVM_SET_GUEST_DEBUG, &debug) < 0)
- warning("KVM_SET_GUEST_DEBUG failed");
+ ret = ioctl(kvm->vm_fd, KVM_SET_TSS_ADDR, 0xfffbd000);
+ if (ret < 0)
+ die_perror("KVM_SET_TSS_ADDR ioctl");
+
+ ret = ioctl(kvm->vm_fd, KVM_CREATE_PIT2, &pit_config);
+ if (ret < 0)
+ die_perror("KVM_CREATE_PIT2 ioctl");
+
+ kvm->ram_size = ram_size;
+
+ if (kvm->ram_size < KVM_32BIT_GAP_START) {
+ kvm->ram_start = mmap(NULL, ram_size, PROT_RW, MAP_ANON_NORESERVE, -1, 0);
+ } else {
+ kvm->ram_start = mmap(NULL, ram_size + KVM_32BIT_GAP_SIZE, PROT_RW, MAP_ANON_NORESERVE, -1, 0);
+ if (kvm->ram_start != MAP_FAILED) {
+ /*
+ * We mprotect the gap (see kvm__init_ram() for details) PROT_NONE so that
+ * if we accidently write to it, we will know.
+ */
+ mprotect(kvm->ram_start + KVM_32BIT_GAP_START, KVM_32BIT_GAP_SIZE, PROT_NONE);
+ }
+ }
+ if (kvm->ram_start == MAP_FAILED)
+ die("out of memory");
+
+ ret = ioctl(kvm->vm_fd, KVM_CREATE_IRQCHIP);
+ if (ret < 0)
+ die_perror("KVM_CREATE_IRQCHIP ioctl");
+
+ return kvm;
}
-#define BOOT_LOADER_SELECTOR 0x0100
+#define BOOT_LOADER_SELECTOR 0x1000
#define BOOT_LOADER_IP 0x0000
#define BOOT_LOADER_SP 0x8000
+#define BOOT_CMDLINE_OFFSET 0x20000
+
+#define BOOT_PROTOCOL_REQUIRED 0x206
+#define LOAD_HIGH 0x01
-static int load_flat_binary(struct kvm *self, int fd)
+static int load_flat_binary(struct kvm *kvm, int fd)
{
void *p;
int nr;
if (lseek(fd, 0, SEEK_SET) < 0)
die_perror("lseek");
- p = guest_real_to_host(self, BOOT_LOADER_SELECTOR, BOOT_LOADER_IP);
+ p = guest_real_to_host(kvm, BOOT_LOADER_SELECTOR, BOOT_LOADER_IP);
while ((nr = read(fd, p, 65536)) > 0)
p += nr;
- self->boot_selector = BOOT_LOADER_SELECTOR;
- self->boot_ip = BOOT_LOADER_IP;
- self->boot_sp = BOOT_LOADER_SP;
+ kvm->boot_selector = BOOT_LOADER_SELECTOR;
+ kvm->boot_ip = BOOT_LOADER_IP;
+ kvm->boot_sp = BOOT_LOADER_SP;
return true;
}
-/*
- * The protected mode kernel part of a modern bzImage is loaded at 1 MB by
- * default.
- */
-#define BZ_KERNEL_START 0x100000UL
-
static const char *BZIMAGE_MAGIC = "HdrS";
-#define BZ_DEFAULT_SETUP_SECTS 4
-
-static bool load_bzimage(struct kvm *self, int fd)
+static bool load_bzimage(struct kvm *kvm, int fd_kernel,
+ int fd_initrd, const char *kernel_cmdline)
{
+ struct boot_params *kern_boot;
unsigned long setup_sects;
struct boot_params boot;
+ size_t cmdline_size;
ssize_t setup_size;
void *p;
int nr;
* memory layout.
*/
- if (lseek(fd, 0, SEEK_SET) < 0)
+ if (lseek(fd_kernel, 0, SEEK_SET) < 0)
die_perror("lseek");
- read(fd, &boot, sizeof(boot));
+ if (read(fd_kernel, &boot, sizeof(boot)) != sizeof(boot))
+ return false;
- if (memcmp(&boot.hdr.header, BZIMAGE_MAGIC, strlen(BZIMAGE_MAGIC)) != 0)
+ if (memcmp(&boot.hdr.header, BZIMAGE_MAGIC, strlen(BZIMAGE_MAGIC)))
return false;
- if (lseek(fd, 0, SEEK_SET) < 0)
+ if (boot.hdr.version < BOOT_PROTOCOL_REQUIRED)
+ die("Too old kernel");
+
+ if (lseek(fd_kernel, 0, SEEK_SET) < 0)
die_perror("lseek");
if (!boot.hdr.setup_sects)
setup_sects = boot.hdr.setup_sects + 1;
setup_size = setup_sects << 9;
- p = guest_real_to_host(self, BOOT_LOADER_SELECTOR, BOOT_LOADER_IP);
+ p = guest_real_to_host(kvm, BOOT_LOADER_SELECTOR, BOOT_LOADER_IP);
- if (read(fd, p, setup_size) != setup_size)
+ /* copy setup.bin to mem*/
+ if (read(fd_kernel, p, setup_size) != setup_size)
die_perror("read");
- p = guest_flat_to_host(self, BZ_KERNEL_START);
+ /* copy vmlinux.bin to BZ_KERNEL_START*/
+ p = guest_flat_to_host(kvm, BZ_KERNEL_START);
- while ((nr = read(fd, p, 65536)) > 0)
+ while ((nr = read(fd_kernel, p, 65536)) > 0)
p += nr;
- self->boot_selector = BOOT_LOADER_SELECTOR;
+ p = guest_flat_to_host(kvm, BOOT_CMDLINE_OFFSET);
+ if (kernel_cmdline) {
+ cmdline_size = strlen(kernel_cmdline) + 1;
+ if (cmdline_size > boot.hdr.cmdline_size)
+ cmdline_size = boot.hdr.cmdline_size;
+
+ memset(p, 0, boot.hdr.cmdline_size);
+ memcpy(p, kernel_cmdline, cmdline_size - 1);
+ }
+
+ kern_boot = guest_real_to_host(kvm, BOOT_LOADER_SELECTOR, 0x00);
+
+ kern_boot->hdr.cmd_line_ptr = BOOT_CMDLINE_OFFSET;
+ kern_boot->hdr.type_of_loader = 0xff;
+ kern_boot->hdr.heap_end_ptr = 0xfe00;
+ kern_boot->hdr.loadflags |= CAN_USE_HEAP;
+
+ /*
+ * Read initrd image into guest memory
+ */
+ if (fd_initrd >= 0) {
+ struct stat initrd_stat;
+ unsigned long addr;
+
+ if (fstat(fd_initrd, &initrd_stat))
+ die_perror("fstat");
+
+ addr = boot.hdr.initrd_addr_max & ~0xfffff;
+ for (;;) {
+ if (addr < BZ_KERNEL_START)
+ die("Not enough memory for initrd");
+ else if (addr < (kvm->ram_size - initrd_stat.st_size))
+ break;
+ addr -= 0x100000;
+ }
+
+ p = guest_flat_to_host(kvm, addr);
+ nr = read(fd_initrd, p, initrd_stat.st_size);
+ if (nr != initrd_stat.st_size)
+ die("Failed to read initrd");
+
+ kern_boot->hdr.ramdisk_image = addr;
+ kern_boot->hdr.ramdisk_size = initrd_stat.st_size;
+ }
+
+ kvm->boot_selector = BOOT_LOADER_SELECTOR;
/*
* The real-mode setup code starts at offset 0x200 of a bzImage. See
* Documentation/x86/boot.txt for details.
*/
- self->boot_ip = BOOT_LOADER_IP + 0x200;
- self->boot_sp = BOOT_LOADER_SP;
+ kvm->boot_ip = BOOT_LOADER_IP + 0x200;
+ kvm->boot_sp = BOOT_LOADER_SP;
return true;
}
-bool kvm__load_kernel(struct kvm *kvm, const char *kernel_filename)
+bool kvm__load_kernel(struct kvm *kvm, const char *kernel_filename,
+ const char *initrd_filename, const char *kernel_cmdline)
{
bool ret;
- int fd;
+ int fd_kernel = -1, fd_initrd = -1;
- fd = open(kernel_filename, O_RDONLY);
- if (fd < 0)
- die("unable to open kernel");
+ fd_kernel = open(kernel_filename, O_RDONLY);
+ if (fd_kernel < 0)
+ die("Unable to open kernel %s", kernel_filename);
+
+ if (initrd_filename) {
+ fd_initrd = open(initrd_filename, O_RDONLY);
+ if (fd_initrd < 0)
+ die("Unable to open initrd %s", initrd_filename);
+ }
+
+ ret = load_bzimage(kvm, fd_kernel, fd_initrd, kernel_cmdline);
+
+ if (initrd_filename)
+ close(fd_initrd);
- ret = load_bzimage(kvm, fd);
if (ret)
goto found_kernel;
- ret = load_flat_binary(kvm, fd);
+ pr_warning("%s is not a bzImage. Trying to load it as a flat binary...", kernel_filename);
+
+ ret = load_flat_binary(kvm, fd_kernel);
if (ret)
goto found_kernel;
+ close(fd_kernel);
+
die("%s is not a valid bzImage or flat binary", kernel_filename);
found_kernel:
+ close(fd_kernel);
+
return ret;
}
-static inline uint64_t ip_flat_to_real(struct kvm *self, uint64_t ip)
+/**
+ * kvm__setup_bios - inject BIOS into guest system memory
+ * @kvm - guest system descriptor
+ *
+ * This function is a main routine where we poke guest memory
+ * and install BIOS there.
+ */
+void kvm__setup_bios(struct kvm *kvm)
{
- uint64_t cs = self->sregs.cs.selector;
-
- return ip - (cs << 4);
-}
+ /* standart minimal configuration */
+ setup_bios(kvm);
-static inline uint64_t ip_real_to_flat(struct kvm *self, uint64_t ip)
-{
- uint64_t cs = self->sregs.cs.selector;
+ /* FIXME: SMP, ACPI and friends here */
- return ip + (cs << 4);
+ /* MP table */
+ mptable_setup(kvm, kvm->nrcpus);
}
-static inline uint32_t selector_to_base(uint16_t selector)
-{
- /*
- * KVM on Intel requires 'base' to be 'selector * 16' in real mode.
- */
- return (uint32_t)selector * 16;
-}
+#define TIMER_INTERVAL_NS 1000000 /* 1 msec */
-void kvm__reset_vcpu(struct kvm *self)
+/*
+ * This function sets up a timer that's used to inject interrupts from the
+ * userspace hypervisor into the guest at periodical intervals. Please note
+ * that clock interrupt, for example, is not handled here.
+ */
+void kvm__start_timer(struct kvm *kvm)
{
- self->sregs = (struct kvm_sregs) {
- .cr0 = 0x60000010ULL,
- .cs = (struct kvm_segment) {
- .selector = self->boot_selector,
- .base = selector_to_base(self->boot_selector),
- .limit = 0xffffU,
- .type = 0x0bU,
- .present = 1,
- .dpl = 0x03,
- .s = 1,
- },
- .ss = (struct kvm_segment) {
- .selector = self->boot_selector,
- .base = selector_to_base(self->boot_selector),
- .limit = 0xffffU,
- .type = 0x03U,
- .present = 1,
- .dpl = 0x03,
- .s = 1,
- },
- .ds = (struct kvm_segment) {
- .selector = self->boot_selector,
- .base = selector_to_base(self->boot_selector),
- .limit = 0xffffU,
- .type = 0x03U,
- .present = 1,
- .dpl = 0x03,
- .s = 1,
- },
- .es = (struct kvm_segment) {
- .selector = self->boot_selector,
- .base = selector_to_base(self->boot_selector),
- .limit = 0xffffU,
- .type = 0x03U,
- .present = 1,
- .dpl = 0x03,
- .s = 1,
- },
- .fs = (struct kvm_segment) {
- .selector = self->boot_selector,
- .base = selector_to_base(self->boot_selector),
- .limit = 0xffffU,
- .type = 0x03U,
- .present = 1,
- .dpl = 0x03,
- .s = 1,
- },
- .gs = (struct kvm_segment) {
- .selector = self->boot_selector,
- .base = selector_to_base(self->boot_selector),
- .limit = 0xffffU,
- .type = 0x03U,
- .present = 1,
- .dpl = 0x03,
- .s = 1,
- },
- .tr = (struct kvm_segment) {
- .limit = 0xffffU,
- .present = 1,
- .type = 0x03U,
- },
- .ldt = (struct kvm_segment) {
- .limit = 0xffffU,
- .present = 1,
- .type = 0x02U,
- },
- .gdt = (struct kvm_dtable) {
- .limit = 0xffffU,
- },
- .idt = (struct kvm_dtable) {
- .limit = 0xffffU,
- },
- };
+ struct itimerspec its;
+ struct sigevent sev;
- if (ioctl(self->vcpu_fd, KVM_SET_SREGS, &self->sregs) < 0)
- die_perror("KVM_SET_SREGS failed");
+ memset(&sev, 0, sizeof(struct sigevent));
+ sev.sigev_value.sival_int = 0;
+ sev.sigev_notify = SIGEV_SIGNAL;
+ sev.sigev_signo = SIGALRM;
- self->regs = (struct kvm_regs) {
- /* We start the guest in 16-bit real mode */
- .rflags = 0x0000000000000002ULL,
+ if (timer_create(CLOCK_REALTIME, &sev, &kvm->timerid) < 0)
+ die("timer_create()");
- .rip = self->boot_ip,
- .rsp = self->boot_sp,
- .rbp = self->boot_sp,
- };
-
- if (self->regs.rip > USHRT_MAX)
- die("ip 0x%" PRIx64 " is too high for real mode", (uint64_t) self->regs.rip);
-
- if (ioctl(self->vcpu_fd, KVM_SET_REGS, &self->regs) < 0)
- die_perror("KVM_SET_REGS failed");
+ its.it_value.tv_sec = TIMER_INTERVAL_NS / 1000000000;
+ its.it_value.tv_nsec = TIMER_INTERVAL_NS % 1000000000;
+ its.it_interval.tv_sec = its.it_value.tv_sec;
+ its.it_interval.tv_nsec = its.it_value.tv_nsec;
+ if (timer_settime(kvm->timerid, 0, &its, NULL) < 0)
+ die("timer_settime()");
}
-void kvm__run(struct kvm *self)
+void kvm__stop_timer(struct kvm *kvm)
{
- if (ioctl(self->vcpu_fd, KVM_RUN, 0) < 0)
- die_perror("KVM_RUN failed");
-}
+ if (kvm->timerid)
+ if (timer_delete(kvm->timerid) < 0)
+ die("timer_delete()");
-static void kvm__emulate_io_out(struct kvm *self, uint16_t port, void *data, int size, uint32_t count)
-{
- fprintf(stderr, "%s port=%x, size=%d, count=%" PRIu32 "\n", __func__, port, size, count);
+ kvm->timerid = 0;
}
-static void kvm__emulate_io_in(struct kvm *self, uint16_t port, void *data, int size, uint32_t count)
+void kvm__irq_line(struct kvm *kvm, int irq, int level)
{
- fprintf(stderr, "%s port=%x, size=%d, count=%" PRIu32 "\n", __func__, port, size, count);
-}
-
-void kvm__emulate_io(struct kvm *self, uint16_t port, void *data, int direction, int size, uint32_t count)
-{
- if (direction == KVM_EXIT_IO_IN)
- kvm__emulate_io_in(self, port, data, size, count);
- else
- kvm__emulate_io_out(self, port, data, size, count);
-}
+ struct kvm_irq_level irq_level;
-static void print_segment(const char *name, struct kvm_segment *seg)
-{
- printf(" %s %04" PRIx16 " %016" PRIx64 " %08" PRIx32 " %02" PRIx8 " %x %x %x %x %x %x %x\n",
- name, (uint16_t) seg->selector, (uint64_t) seg->base, (uint32_t) seg->limit,
- (uint8_t) seg->type, seg->present, seg->dpl, seg->db, seg->s, seg->l, seg->g, seg->avl);
-}
+ irq_level = (struct kvm_irq_level) {
+ {
+ .irq = irq,
+ },
+ .level = level,
+ };
-void kvm__show_registers(struct kvm *self)
-{
- unsigned long cr0, cr2, cr3;
- unsigned long cr4, cr8;
- unsigned long rax, rbx, rcx;
- unsigned long rdx, rsi, rdi;
- unsigned long rbp, r8, r9;
- unsigned long r10, r11, r12;
- unsigned long r13, r14, r15;
- unsigned long rip, rsp;
- struct kvm_sregs sregs;
- unsigned long rflags;
- struct kvm_regs regs;
- int i;
-
- if (ioctl(self->vcpu_fd, KVM_GET_REGS, ®s) < 0)
- die("KVM_GET_REGS failed");
-
- rflags = regs.rflags;
-
- rip = regs.rip; rsp = regs.rsp;
- rax = regs.rax; rbx = regs.rbx; rcx = regs.rcx;
- rdx = regs.rdx; rsi = regs.rsi; rdi = regs.rdi;
- rbp = regs.rbp; r8 = regs.r8; r9 = regs.r9;
- r10 = regs.r10; r11 = regs.r11; r12 = regs.r12;
- r13 = regs.r13; r14 = regs.r14; r15 = regs.r15;
-
- printf("Registers:\n");
- printf(" rip: %016lx rsp: %016lx flags: %016lx\n", rip, rsp, rflags);
- printf(" rax: %016lx ebx: %016lx ecx: %016lx\n", rax, rbx, rcx);
- printf(" rdx: %016lx rsi: %016lx rdi: %016lx\n", rdx, rsi, rdi);
- printf(" rbp: %016lx r8: %016lx r9: %016lx\n", rbp, r8, r9);
- printf(" r10: %016lx r11: %016lx r12: %016lx\n", r10, r11, r12);
- printf(" r13: %016lx r14: %016lx r15: %016lx\n", r13, r14, r15);
-
- if (ioctl(self->vcpu_fd, KVM_GET_SREGS, &sregs) < 0)
- die("KVM_GET_REGS failed");
-
- cr0 = sregs.cr0; cr2 = sregs.cr2; cr3 = sregs.cr3;
- cr4 = sregs.cr4; cr8 = sregs.cr8;
-
- printf(" cr0: %016lx cr2: %016lx cr3: %016lx\n", cr0, cr2, cr3);
- printf(" cr4: %016lx cr8: %016lx\n", cr4, cr8);
- printf("Segment registers:\n");
- printf(" register selector base limit type p dpl db s l g avl\n");
- print_segment("cs ", &sregs.cs);
- print_segment("ss ", &sregs.ss);
- print_segment("ds ", &sregs.ds);
- print_segment("es ", &sregs.es);
- print_segment("fs ", &sregs.fs);
- print_segment("gs ", &sregs.gs);
- print_segment("tr ", &sregs.tr);
- print_segment("ldt", &sregs.ldt);
- printf(" [ efer: %016lx apic base: %016lx ]\n", (uint64_t) sregs.efer, (uint64_t) sregs.apic_base);
- printf("Interrupt bitmap:\n");
- printf(" ");
- for (i = 0; i < (KVM_NR_INTERRUPTS + 63) / 64; i++)
- printf("%016lx ", (uint64_t) sregs.interrupt_bitmap[i]);
- printf("\n");
+ if (ioctl(kvm->vm_fd, KVM_IRQ_LINE, &irq_level) < 0)
+ die_perror("KVM_IRQ_LINE failed");
}
-void kvm__show_code(struct kvm *self)
+void kvm__dump_mem(struct kvm *kvm, unsigned long addr, unsigned long size)
{
- unsigned int code_bytes = 64;
- unsigned int code_prologue = code_bytes * 43 / 64;
- unsigned int code_len = code_bytes;
- unsigned char c;
- unsigned int i;
- uint8_t *ip;
-
- if (ioctl(self->vcpu_fd, KVM_GET_REGS, &self->regs) < 0)
- die("KVM_GET_REGS failed");
+ unsigned char *p;
+ unsigned long n;
- if (ioctl(self->vcpu_fd, KVM_GET_SREGS, &self->sregs) < 0)
- die("KVM_GET_SREGS failed");
+ size &= ~7; /* mod 8 */
+ if (!size)
+ return;
- ip = guest_flat_to_host(self, ip_real_to_flat(self, self->regs.rip) - code_prologue);
+ p = guest_flat_to_host(kvm, addr);
- printf("Code: ");
+ for (n = 0; n < size; n += 8) {
+ if (!host_ptr_in_ram(kvm, p + n))
+ break;
- for (i = 0; i < code_len; i++, ip++) {
- c = *ip;
-
- if (ip == guest_flat_to_host(self, ip_real_to_flat(self, self->regs.rip)))
- printf("<%02x> ", c);
- else
- printf("%02x ", c);
+ printf(" 0x%08lx: %02x %02x %02x %02x %02x %02x %02x %02x\n",
+ addr + n, p[n + 0], p[n + 1], p[n + 2], p[n + 3],
+ p[n + 4], p[n + 5], p[n + 6], p[n + 7]);
}
-
- printf("\n");
}