diff --git a/kvm-all.c b/kvm-all.c new file mode 100644 index 0000000000..c3a46e2438 --- /dev/null +++ b/kvm-all.c @@ -0,0 +1,374 @@ +/* + * QEMU KVM support + * + * Copyright IBM, Corp. 2008 + * + * Authors: + * Anthony Liguori + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include +#include +#include + +#include + +#include "qemu-common.h" +#include "sysemu.h" +#include "kvm.h" + +//#define DEBUG_KVM + +#ifdef DEBUG_KVM +#define dprintf(fmt, ...) \ + do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0) +#else +#define dprintf(fmt, ...) \ + do { } while (0) +#endif + +typedef struct kvm_userspace_memory_region KVMSlot; + +int kvm_allowed = 0; + +struct KVMState +{ + KVMSlot slots[32]; + int fd; + int vmfd; +}; + +static KVMState *kvm_state; + +static KVMSlot *kvm_alloc_slot(KVMState *s) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(s->slots); i++) { + if (s->slots[i].memory_size == 0) + return &s->slots[i]; + } + + return NULL; +} + +static KVMSlot *kvm_lookup_slot(KVMState *s, target_phys_addr_t start_addr) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(s->slots); i++) { + KVMSlot *mem = &s->slots[i]; + + if (start_addr >= mem->guest_phys_addr && + start_addr < (mem->guest_phys_addr + mem->memory_size)) + return mem; + } + + return NULL; +} + +int kvm_init_vcpu(CPUState *env) +{ + KVMState *s = kvm_state; + long mmap_size; + int ret; + + dprintf("kvm_init_vcpu\n"); + + ret = kvm_vm_ioctl(s, KVM_CREATE_VCPU, + (void *)(unsigned long)env->cpu_index); + if (ret < 0) { + dprintf("kvm_create_vcpu failed\n"); + goto err; + } + + env->kvm_fd = ret; + env->kvm_state = s; + + mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0); + if (mmap_size < 0) { + dprintf("KVM_GET_VCPU_MMAP_SIZE failed\n"); + goto err; + } + + env->kvm_run = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, + env->kvm_fd, 0); + if (env->kvm_run == MAP_FAILED) { + ret = -errno; + dprintf("mmap'ing vcpu state failed\n"); + goto err; + } + + ret = kvm_arch_init_vcpu(env); + +err: + return ret; +} + +int kvm_init(int smp_cpus) +{ + KVMState *s; + int ret; + int i; + + if (smp_cpus > 1) + return -EINVAL; + + s = qemu_mallocz(sizeof(KVMState)); + if (s == NULL) + return -ENOMEM; + + for (i = 0; i < ARRAY_SIZE(s->slots); i++) + s->slots[i].slot = i; + + s->vmfd = -1; + s->fd = open("/dev/kvm", O_RDWR); + if (s->fd == -1) { + fprintf(stderr, "Could not access KVM kernel module: %m\n"); + ret = -errno; + goto err; + } + + ret = kvm_ioctl(s, KVM_GET_API_VERSION, 0); + if (ret < KVM_API_VERSION) { + if (ret > 0) + ret = -EINVAL; + fprintf(stderr, "kvm version too old\n"); + goto err; + } + + if (ret > KVM_API_VERSION) { + ret = -EINVAL; + fprintf(stderr, "kvm version not supported\n"); + goto err; + } + + s->vmfd = kvm_ioctl(s, KVM_CREATE_VM, 0); + if (s->vmfd < 0) + goto err; + + /* initially, KVM allocated its own memory and we had to jump through + * hooks to make phys_ram_base point to this. Modern versions of KVM + * just use a user allocated buffer so we can use phys_ram_base + * unmodified. Make sure we have a sufficiently modern version of KVM. + */ + ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, (void *)KVM_CAP_USER_MEMORY); + if (ret <= 0) { + if (ret == 0) + ret = -EINVAL; + fprintf(stderr, "kvm does not support KVM_CAP_USER_MEMORY\n"); + goto err; + } + + ret = kvm_arch_init(s, smp_cpus); + if (ret < 0) + goto err; + + kvm_state = s; + + return 0; + +err: + if (s) { + if (s->vmfd != -1) + close(s->vmfd); + if (s->fd != -1) + close(s->fd); + } + qemu_free(s); + + return ret; +} + +static int kvm_handle_io(CPUState *env, uint16_t port, void *data, + int direction, int size, uint32_t count) +{ + int i; + uint8_t *ptr = data; + + for (i = 0; i < count; i++) { + if (direction == KVM_EXIT_IO_IN) { + switch (size) { + case 1: + stb_p(ptr, cpu_inb(env, port)); + break; + case 2: + stw_p(ptr, cpu_inw(env, port)); + break; + case 4: + stl_p(ptr, cpu_inl(env, port)); + break; + } + } else { + switch (size) { + case 1: + cpu_outb(env, port, ldub_p(ptr)); + break; + case 2: + cpu_outw(env, port, lduw_p(ptr)); + break; + case 4: + cpu_outl(env, port, ldl_p(ptr)); + break; + } + } + + ptr += size; + } + + return 1; +} + +int kvm_cpu_exec(CPUState *env) +{ + struct kvm_run *run = env->kvm_run; + int ret; + + dprintf("kvm_cpu_exec()\n"); + + do { + kvm_arch_pre_run(env, run); + + if ((env->interrupt_request & CPU_INTERRUPT_EXIT)) { + dprintf("interrupt exit requested\n"); + ret = 0; + break; + } + + ret = kvm_vcpu_ioctl(env, KVM_RUN, 0); + kvm_arch_post_run(env, run); + + if (ret == -EINTR || ret == -EAGAIN) { + dprintf("io window exit\n"); + ret = 0; + break; + } + + if (ret < 0) { + dprintf("kvm run failed %s\n", strerror(-ret)); + abort(); + } + + ret = 0; /* exit loop */ + switch (run->exit_reason) { + case KVM_EXIT_IO: + dprintf("handle_io\n"); + ret = kvm_handle_io(env, run->io.port, + (uint8_t *)run + run->io.data_offset, + run->io.direction, + run->io.size, + run->io.count); + break; + case KVM_EXIT_MMIO: + dprintf("handle_mmio\n"); + cpu_physical_memory_rw(run->mmio.phys_addr, + run->mmio.data, + run->mmio.len, + run->mmio.is_write); + ret = 1; + break; + case KVM_EXIT_IRQ_WINDOW_OPEN: + dprintf("irq_window_open\n"); + break; + case KVM_EXIT_SHUTDOWN: + dprintf("shutdown\n"); + qemu_system_reset_request(); + ret = 1; + break; + case KVM_EXIT_UNKNOWN: + dprintf("kvm_exit_unknown\n"); + break; + case KVM_EXIT_FAIL_ENTRY: + dprintf("kvm_exit_fail_entry\n"); + break; + case KVM_EXIT_EXCEPTION: + dprintf("kvm_exit_exception\n"); + break; + case KVM_EXIT_DEBUG: + dprintf("kvm_exit_debug\n"); + break; + default: + dprintf("kvm_arch_handle_exit\n"); + ret = kvm_arch_handle_exit(env, run); + break; + } + } while (ret > 0); + + return ret; +} + +void kvm_set_phys_mem(target_phys_addr_t start_addr, + ram_addr_t size, + ram_addr_t phys_offset) +{ + KVMState *s = kvm_state; + ram_addr_t flags = phys_offset & ~TARGET_PAGE_MASK; + KVMSlot *mem; + + /* KVM does not support read-only slots */ + phys_offset &= ~IO_MEM_ROM; + + mem = kvm_lookup_slot(s, start_addr); + if (mem) { + if (flags == IO_MEM_UNASSIGNED) { + mem->memory_size = 0; + mem->guest_phys_addr = start_addr; + mem->userspace_addr = 0; + mem->flags = 0; + + kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, mem); + } else if (start_addr >= mem->guest_phys_addr && + (start_addr + size) <= (mem->guest_phys_addr + mem->memory_size)) + return; + } + + /* KVM does not need to know about this memory */ + if (flags >= IO_MEM_UNASSIGNED) + return; + + mem = kvm_alloc_slot(s); + mem->memory_size = size; + mem->guest_phys_addr = start_addr; + mem->userspace_addr = (unsigned long)(phys_ram_base + phys_offset); + mem->flags = 0; + + kvm_vm_ioctl(s, KVM_SET_USER_MEMORY_REGION, mem); + /* FIXME deal with errors */ +} + +int kvm_ioctl(KVMState *s, int type, void *data) +{ + int ret; + + ret = ioctl(s->fd, type, data); + if (ret == -1) + ret = -errno; + + return ret; +} + +int kvm_vm_ioctl(KVMState *s, int type, void *data) +{ + int ret; + + ret = ioctl(s->vmfd, type, data); + if (ret == -1) + ret = -errno; + + return ret; +} + +int kvm_vcpu_ioctl(CPUState *env, int type, void *data) +{ + int ret; + + ret = ioctl(env->kvm_fd, type, data); + if (ret == -1) + ret = -errno; + + return ret; +} diff --git a/kvm.h b/kvm.h new file mode 100644 index 0000000000..4af48abb17 --- /dev/null +++ b/kvm.h @@ -0,0 +1,68 @@ +/* + * QEMU KVM support + * + * Copyright IBM, Corp. 2008 + * + * Authors: + * Anthony Liguori + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef QEMU_KVM_H +#define QEMU_KVM_H + +#include "config.h" + +#ifdef CONFIG_KVM +extern int kvm_allowed; + +#define kvm_enabled() (kvm_allowed) +#else +#define kvm_enabled() (0) +#endif + +struct kvm_run; + +/* external API */ + +int kvm_init(int smp_cpus); + +int kvm_init_vcpu(CPUState *env); + +int kvm_cpu_exec(CPUState *env); + +void kvm_set_phys_mem(target_phys_addr_t start_addr, + ram_addr_t size, + ram_addr_t phys_offset); + +/* internal API */ + +struct KVMState; +typedef struct KVMState KVMState; + +int kvm_ioctl(KVMState *s, int type, void *data); + +int kvm_vm_ioctl(KVMState *s, int type, void *data); + +int kvm_vcpu_ioctl(CPUState *env, int type, void *data); + +/* Arch specific hooks */ + +int kvm_arch_post_run(CPUState *env, struct kvm_run *run); + +int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run); + +int kvm_arch_pre_run(CPUState *env, struct kvm_run *run); + +int kvm_arch_get_registers(CPUState *env); + +int kvm_arch_put_registers(CPUState *env); + +int kvm_arch_init(KVMState *s, int smp_cpus); + +int kvm_arch_init_vcpu(CPUState *env); + +#endif diff --git a/target-i386/kvm.c b/target-i386/kvm.c new file mode 100644 index 0000000000..f22f30a137 --- /dev/null +++ b/target-i386/kvm.c @@ -0,0 +1,638 @@ +/* + * QEMU KVM support + * + * Copyright (C) 2006-2008 Qumranet Technologies + * Copyright IBM, Corp. 2008 + * + * Authors: + * Anthony Liguori + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include +#include +#include + +#include + +#include "qemu-common.h" +#include "sysemu.h" +#include "kvm.h" +#include "cpu.h" + +//#define DEBUG_KVM + +#ifdef DEBUG_KVM +#define dprintf(fmt, ...) \ + do { fprintf(stderr, fmt, ## __VA_ARGS__); } while (0) +#else +#define dprintf(fmt, ...) \ + do { } while (0) +#endif + +int kvm_arch_init_vcpu(CPUState *env) +{ + struct { + struct kvm_cpuid cpuid; + struct kvm_cpuid_entry entries[100]; + } __attribute__((packed)) cpuid_data; + int limit, i, cpuid_i; + uint32_t eax, ebx, ecx, edx; + + cpuid_i = 0; + + cpu_x86_cpuid(env, 0, &eax, &ebx, &ecx, &edx); + limit = eax; + + for (i = 0; i <= limit; i++) { + struct kvm_cpuid_entry *c = &cpuid_data.entries[cpuid_i++]; + + cpu_x86_cpuid(env, i, &eax, &ebx, &ecx, &edx); + c->function = i; + c->eax = eax; + c->ebx = ebx; + c->ecx = ecx; + c->edx = edx; + } + + cpu_x86_cpuid(env, 0x80000000, &eax, &ebx, &ecx, &edx); + limit = eax; + + for (i = 0x80000000; i <= limit; i++) { + struct kvm_cpuid_entry *c = &cpuid_data.entries[cpuid_i++]; + + cpu_x86_cpuid(env, i, &eax, &ebx, &ecx, &edx); + c->function = i; + c->eax = eax; + c->ebx = ebx; + c->ecx = ecx; + c->edx = edx; + } + + cpuid_data.cpuid.nent = cpuid_i; + + return kvm_vcpu_ioctl(env, KVM_SET_CPUID, &cpuid_data); +} + +static int kvm_has_msr_star(CPUState *env) +{ + static int has_msr_star; + int ret; + + /* first time */ + if (has_msr_star == 0) { + struct kvm_msr_list msr_list, *kvm_msr_list; + + has_msr_star = -1; + + /* Obtain MSR list from KVM. These are the MSRs that we must + * save/restore */ + ret = kvm_ioctl(env->kvm_state, KVM_GET_MSR_INDEX_LIST, &msr_list); + if (ret < 0) + return 0; + + msr_list.nmsrs = 0; + kvm_msr_list = qemu_mallocz(sizeof(msr_list) + + msr_list.nmsrs * sizeof(msr_list.indices[0])); + if (kvm_msr_list == NULL) + return 0; + + ret = kvm_ioctl(env->kvm_state, KVM_GET_MSR_INDEX_LIST, kvm_msr_list); + if (ret >= 0) { + int i; + + for (i = 0; i < kvm_msr_list->nmsrs; i++) { + if (kvm_msr_list->indices[i] == MSR_STAR) { + has_msr_star = 1; + break; + } + } + } + + free(kvm_msr_list); + } + + if (has_msr_star == 1) + return 1; + return 0; +} + +int kvm_arch_init(KVMState *s, int smp_cpus) +{ + int ret; + + /* create vm86 tss. KVM uses vm86 mode to emulate 16-bit code + * directly. In order to use vm86 mode, a TSS is needed. Since this + * must be part of guest physical memory, we need to allocate it. Older + * versions of KVM just assumed that it would be at the end of physical + * memory but that doesn't work with more than 4GB of memory. We simply + * refuse to work with those older versions of KVM. */ + ret = kvm_ioctl(s, KVM_CHECK_EXTENSION, (void *)KVM_CAP_SET_TSS_ADDR); + if (ret <= 0) { + fprintf(stderr, "kvm does not support KVM_CAP_SET_TSS_ADDR\n"); + return ret; + } + + /* this address is 3 pages before the bios, and the bios should present + * as unavaible memory. FIXME, need to ensure the e820 map deals with + * this? + */ + return kvm_vm_ioctl(s, KVM_SET_TSS_ADDR, (void *)0xfffbd000); +} + +static void set_v8086_seg(struct kvm_segment *lhs, const SegmentCache *rhs) +{ + lhs->selector = rhs->selector; + lhs->base = rhs->base; + lhs->limit = rhs->limit; + lhs->type = 3; + lhs->present = 1; + lhs->dpl = 3; + lhs->db = 0; + lhs->s = 1; + lhs->l = 0; + lhs->g = 0; + lhs->avl = 0; + lhs->unusable = 0; +} + +static void set_seg(struct kvm_segment *lhs, const SegmentCache *rhs) +{ + unsigned flags = rhs->flags; + lhs->selector = rhs->selector; + lhs->base = rhs->base; + lhs->limit = rhs->limit; + lhs->type = (flags >> DESC_TYPE_SHIFT) & 15; + lhs->present = (flags & DESC_P_MASK) != 0; + lhs->dpl = rhs->selector & 3; + lhs->db = (flags >> DESC_B_SHIFT) & 1; + lhs->s = (flags & DESC_S_MASK) != 0; + lhs->l = (flags >> DESC_L_SHIFT) & 1; + lhs->g = (flags & DESC_G_MASK) != 0; + lhs->avl = (flags & DESC_AVL_MASK) != 0; + lhs->unusable = 0; +} + +static void get_seg(SegmentCache *lhs, const struct kvm_segment *rhs) +{ + lhs->selector = rhs->selector; + lhs->base = rhs->base; + lhs->limit = rhs->limit; + lhs->flags = + (rhs->type << DESC_TYPE_SHIFT) + | (rhs->present * DESC_P_MASK) + | (rhs->dpl << DESC_DPL_SHIFT) + | (rhs->db << DESC_B_SHIFT) + | (rhs->s * DESC_S_MASK) + | (rhs->l << DESC_L_SHIFT) + | (rhs->g * DESC_G_MASK) + | (rhs->avl * DESC_AVL_MASK); +} + +static void kvm_getput_reg(__u64 *kvm_reg, target_ulong *qemu_reg, int set) +{ + if (set) + *kvm_reg = *qemu_reg; + else + *qemu_reg = *kvm_reg; +} + +static int kvm_getput_regs(CPUState *env, int set) +{ + struct kvm_regs regs; + int ret = 0; + + if (!set) { + ret = kvm_vcpu_ioctl(env, KVM_GET_REGS, ®s); + if (ret < 0) + return ret; + } + + kvm_getput_reg(®s.rax, &env->regs[R_EAX], set); + kvm_getput_reg(®s.rbx, &env->regs[R_EBX], set); + kvm_getput_reg(®s.rcx, &env->regs[R_ECX], set); + kvm_getput_reg(®s.rdx, &env->regs[R_EDX], set); + kvm_getput_reg(®s.rsi, &env->regs[R_ESI], set); + kvm_getput_reg(®s.rdi, &env->regs[R_EDI], set); + kvm_getput_reg(®s.rsp, &env->regs[R_ESP], set); + kvm_getput_reg(®s.rbp, &env->regs[R_EBP], set); +#ifdef TARGET_X86_64 + kvm_getput_reg(®s.r8, &env->regs[8], set); + kvm_getput_reg(®s.r9, &env->regs[9], set); + kvm_getput_reg(®s.r10, &env->regs[10], set); + kvm_getput_reg(®s.r11, &env->regs[11], set); + kvm_getput_reg(®s.r12, &env->regs[12], set); + kvm_getput_reg(®s.r13, &env->regs[13], set); + kvm_getput_reg(®s.r14, &env->regs[14], set); + kvm_getput_reg(®s.r15, &env->regs[15], set); +#endif + + kvm_getput_reg(®s.rflags, &env->eflags, set); + kvm_getput_reg(®s.rip, &env->eip, set); + + if (set) + ret = kvm_vcpu_ioctl(env, KVM_SET_REGS, ®s); + + return ret; +} + +static int kvm_put_fpu(CPUState *env) +{ + struct kvm_fpu fpu; + int i; + + memset(&fpu, 0, sizeof fpu); + fpu.fsw = env->fpus & ~(7 << 11); + fpu.fsw |= (env->fpstt & 7) << 11; + fpu.fcw = env->fpuc; + for (i = 0; i < 8; ++i) + fpu.ftwx |= (!env->fptags[i]) << i; + memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs); + memcpy(fpu.xmm, env->xmm_regs, sizeof env->xmm_regs); + fpu.mxcsr = env->mxcsr; + + return kvm_vcpu_ioctl(env, KVM_SET_FPU, &fpu); +} + +static int kvm_put_sregs(CPUState *env) +{ + struct kvm_sregs sregs; + + memcpy(sregs.interrupt_bitmap, + env->interrupt_bitmap, + sizeof(sregs.interrupt_bitmap)); + + if ((env->eflags & VM_MASK)) { + set_v8086_seg(&sregs.cs, &env->segs[R_CS]); + set_v8086_seg(&sregs.ds, &env->segs[R_DS]); + set_v8086_seg(&sregs.es, &env->segs[R_ES]); + set_v8086_seg(&sregs.fs, &env->segs[R_FS]); + set_v8086_seg(&sregs.gs, &env->segs[R_GS]); + set_v8086_seg(&sregs.ss, &env->segs[R_SS]); + } else { + set_seg(&sregs.cs, &env->segs[R_CS]); + set_seg(&sregs.ds, &env->segs[R_DS]); + set_seg(&sregs.es, &env->segs[R_ES]); + set_seg(&sregs.fs, &env->segs[R_FS]); + set_seg(&sregs.gs, &env->segs[R_GS]); + set_seg(&sregs.ss, &env->segs[R_SS]); + + if (env->cr[0] & CR0_PE_MASK) { + /* force ss cpl to cs cpl */ + sregs.ss.selector = (sregs.ss.selector & ~3) | + (sregs.cs.selector & 3); + sregs.ss.dpl = sregs.ss.selector & 3; + } + } + + set_seg(&sregs.tr, &env->tr); + set_seg(&sregs.ldt, &env->ldt); + + sregs.idt.limit = env->idt.limit; + sregs.idt.base = env->idt.base; + sregs.gdt.limit = env->gdt.limit; + sregs.gdt.base = env->gdt.base; + + sregs.cr0 = env->cr[0]; + sregs.cr2 = env->cr[2]; + sregs.cr3 = env->cr[3]; + sregs.cr4 = env->cr[4]; + + sregs.cr8 = cpu_get_apic_tpr(env); + sregs.apic_base = cpu_get_apic_base(env); + + sregs.efer = env->efer; + + return kvm_vcpu_ioctl(env, KVM_SET_SREGS, &sregs); +} + +static void kvm_msr_entry_set(struct kvm_msr_entry *entry, + uint32_t index, uint64_t value) +{ + entry->index = index; + entry->data = value; +} + +static int kvm_put_msrs(CPUState *env) +{ + struct { + struct kvm_msrs info; + struct kvm_msr_entry entries[100]; + } msr_data; + struct kvm_msr_entry *msrs = msr_data.entries; + int n = 0; + + kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_CS, env->sysenter_cs); + kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_ESP, env->sysenter_esp); + kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_EIP, env->sysenter_eip); + if (kvm_has_msr_star(env)) + kvm_msr_entry_set(&msrs[n++], MSR_STAR, env->star); + kvm_msr_entry_set(&msrs[n++], MSR_IA32_TSC, env->tsc); +#ifdef TARGET_X86_64 + /* FIXME if lm capable */ + kvm_msr_entry_set(&msrs[n++], MSR_CSTAR, env->cstar); + kvm_msr_entry_set(&msrs[n++], MSR_KERNELGSBASE, env->kernelgsbase); + kvm_msr_entry_set(&msrs[n++], MSR_FMASK, env->fmask); + kvm_msr_entry_set(&msrs[n++], MSR_LSTAR, env->lstar); +#endif + msr_data.info.nmsrs = n; + + return kvm_vcpu_ioctl(env, KVM_SET_MSRS, &msr_data); + +} + + +static int kvm_get_fpu(CPUState *env) +{ + struct kvm_fpu fpu; + int i, ret; + + ret = kvm_vcpu_ioctl(env, KVM_GET_FPU, &fpu); + if (ret < 0) + return ret; + + env->fpstt = (fpu.fsw >> 11) & 7; + env->fpus = fpu.fsw; + env->fpuc = fpu.fcw; + for (i = 0; i < 8; ++i) + env->fptags[i] = !((fpu.ftwx >> i) & 1); + memcpy(env->fpregs, fpu.fpr, sizeof env->fpregs); + memcpy(env->xmm_regs, fpu.xmm, sizeof env->xmm_regs); + env->mxcsr = fpu.mxcsr; + + return 0; +} + +static int kvm_get_sregs(CPUState *env) +{ + struct kvm_sregs sregs; + uint32_t hflags; + int ret; + + ret = kvm_vcpu_ioctl(env, KVM_GET_SREGS, &sregs); + if (ret < 0) + return ret; + + memcpy(env->interrupt_bitmap, + sregs.interrupt_bitmap, + sizeof(sregs.interrupt_bitmap)); + + get_seg(&env->segs[R_CS], &sregs.cs); + get_seg(&env->segs[R_DS], &sregs.ds); + get_seg(&env->segs[R_ES], &sregs.es); + get_seg(&env->segs[R_FS], &sregs.fs); + get_seg(&env->segs[R_GS], &sregs.gs); + get_seg(&env->segs[R_SS], &sregs.ss); + + get_seg(&env->tr, &sregs.tr); + get_seg(&env->ldt, &sregs.ldt); + + env->idt.limit = sregs.idt.limit; + env->idt.base = sregs.idt.base; + env->gdt.limit = sregs.gdt.limit; + env->gdt.base = sregs.gdt.base; + + env->cr[0] = sregs.cr0; + env->cr[2] = sregs.cr2; + env->cr[3] = sregs.cr3; + env->cr[4] = sregs.cr4; + + cpu_set_apic_base(env, sregs.apic_base); + + env->efer = sregs.efer; + //cpu_set_apic_tpr(env, sregs.cr8); + +#define HFLAG_COPY_MASK ~( \ + HF_CPL_MASK | HF_PE_MASK | HF_MP_MASK | HF_EM_MASK | \ + HF_TS_MASK | HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK | \ + HF_OSFXSR_MASK | HF_LMA_MASK | HF_CS32_MASK | \ + HF_SS32_MASK | HF_CS64_MASK | HF_ADDSEG_MASK) + + + + hflags = (env->segs[R_CS].flags >> DESC_DPL_SHIFT) & HF_CPL_MASK; + hflags |= (env->cr[0] & CR0_PE_MASK) << (HF_PE_SHIFT - CR0_PE_SHIFT); + hflags |= (env->cr[0] << (HF_MP_SHIFT - CR0_MP_SHIFT)) & + (HF_MP_MASK | HF_EM_MASK | HF_TS_MASK); + hflags |= (env->eflags & (HF_TF_MASK | HF_VM_MASK | HF_IOPL_MASK)); + hflags |= (env->cr[4] & CR4_OSFXSR_MASK) << + (HF_OSFXSR_SHIFT - CR4_OSFXSR_SHIFT); + + if (env->efer & MSR_EFER_LMA) { + hflags |= HF_LMA_MASK; + } + + if ((hflags & HF_LMA_MASK) && (env->segs[R_CS].flags & DESC_L_MASK)) { + hflags |= HF_CS32_MASK | HF_SS32_MASK | HF_CS64_MASK; + } else { + hflags |= (env->segs[R_CS].flags & DESC_B_MASK) >> + (DESC_B_SHIFT - HF_CS32_SHIFT); + hflags |= (env->segs[R_SS].flags & DESC_B_MASK) >> + (DESC_B_SHIFT - HF_SS32_SHIFT); + if (!(env->cr[0] & CR0_PE_MASK) || + (env->eflags & VM_MASK) || + !(hflags & HF_CS32_MASK)) { + hflags |= HF_ADDSEG_MASK; + } else { + hflags |= ((env->segs[R_DS].base | + env->segs[R_ES].base | + env->segs[R_SS].base) != 0) << + HF_ADDSEG_SHIFT; + } + } + env->hflags = (env->hflags & HFLAG_COPY_MASK) | hflags; + env->cc_src = env->eflags & (CC_O | CC_S | CC_Z | CC_A | CC_P | CC_C); + env->df = 1 - (2 * ((env->eflags >> 10) & 1)); + env->cc_op = CC_OP_EFLAGS; + env->eflags &= ~(DF_MASK | CC_O | CC_S | CC_Z | CC_A | CC_P | CC_C); + + return 0; +} + +static int kvm_get_msrs(CPUState *env) +{ + struct { + struct kvm_msrs info; + struct kvm_msr_entry entries[100]; + } msr_data; + struct kvm_msr_entry *msrs = msr_data.entries; + int ret, i, n; + + n = 0; + msrs[n++].index = MSR_IA32_SYSENTER_CS; + msrs[n++].index = MSR_IA32_SYSENTER_ESP; + msrs[n++].index = MSR_IA32_SYSENTER_EIP; + if (kvm_has_msr_star(env)) + msrs[n++].index = MSR_STAR; + msrs[n++].index = MSR_IA32_TSC; +#ifdef TARGET_X86_64 + /* FIXME lm_capable_kernel */ + msrs[n++].index = MSR_CSTAR; + msrs[n++].index = MSR_KERNELGSBASE; + msrs[n++].index = MSR_FMASK; + msrs[n++].index = MSR_LSTAR; +#endif + msr_data.info.nmsrs = n; + ret = kvm_vcpu_ioctl(env, KVM_GET_MSRS, &msr_data); + if (ret < 0) + return ret; + + for (i = 0; i < ret; i++) { + switch (msrs[i].index) { + case MSR_IA32_SYSENTER_CS: + env->sysenter_cs = msrs[i].data; + break; + case MSR_IA32_SYSENTER_ESP: + env->sysenter_esp = msrs[i].data; + break; + case MSR_IA32_SYSENTER_EIP: + env->sysenter_eip = msrs[i].data; + break; + case MSR_STAR: + env->star = msrs[i].data; + break; +#ifdef TARGET_X86_64 + case MSR_CSTAR: + env->cstar = msrs[i].data; + break; + case MSR_KERNELGSBASE: + env->kernelgsbase = msrs[i].data; + break; + case MSR_FMASK: + env->fmask = msrs[i].data; + break; + case MSR_LSTAR: + env->lstar = msrs[i].data; + break; +#endif + case MSR_IA32_TSC: + env->tsc = msrs[i].data; + break; + } + } + + return 0; +} + +int kvm_arch_put_registers(CPUState *env) +{ + int ret; + + ret = kvm_getput_regs(env, 1); + if (ret < 0) + return ret; + + ret = kvm_put_fpu(env); + if (ret < 0) + return ret; + + ret = kvm_put_sregs(env); + if (ret < 0) + return ret; + + ret = kvm_put_msrs(env); + if (ret < 0) + return ret; + + return 0; +} + +int kvm_arch_get_registers(CPUState *env) +{ + int ret; + + ret = kvm_getput_regs(env, 0); + if (ret < 0) + return ret; + + ret = kvm_get_fpu(env); + if (ret < 0) + return ret; + + ret = kvm_get_sregs(env); + if (ret < 0) + return ret; + + ret = kvm_get_msrs(env); + if (ret < 0) + return ret; + + return 0; +} + +int kvm_arch_pre_run(CPUState *env, struct kvm_run *run) +{ + /* Try to inject an interrupt if the guest can accept it */ + if (run->ready_for_interrupt_injection && + (env->interrupt_request & CPU_INTERRUPT_HARD) && + (env->eflags & IF_MASK)) { + int irq; + + env->interrupt_request &= ~CPU_INTERRUPT_HARD; + irq = cpu_get_pic_interrupt(env); + if (irq >= 0) { + struct kvm_interrupt intr; + intr.irq = irq; + /* FIXME: errors */ + dprintf("injected interrupt %d\n", irq); + kvm_vcpu_ioctl(env, KVM_INTERRUPT, &intr); + } + } + + /* If we have an interrupt but the guest is not ready to receive an + * interrupt, request an interrupt window exit. This will + * cause a return to userspace as soon as the guest is ready to + * receive interrupts. */ + if ((env->interrupt_request & CPU_INTERRUPT_HARD)) + run->request_interrupt_window = 1; + else + run->request_interrupt_window = 0; + + dprintf("setting tpr\n"); + run->cr8 = cpu_get_apic_tpr(env); + + return 0; +} + +int kvm_arch_post_run(CPUState *env, struct kvm_run *run) +{ + if (run->if_flag) + env->eflags |= IF_MASK; + else + env->eflags &= ~IF_MASK; + + cpu_set_apic_tpr(env, run->cr8); + cpu_set_apic_base(env, run->apic_base); + + return 0; +} + +static int kvm_handle_halt(CPUState *env) +{ + if (!((env->interrupt_request & CPU_INTERRUPT_HARD) && + (env->eflags & IF_MASK)) && + !(env->interrupt_request & CPU_INTERRUPT_NMI)) { + env->halted = 1; + env->exception_index = EXCP_HLT; + return 0; + } + + return 1; +} + +int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run) +{ + int ret = 0; + + switch (run->exit_reason) { + case KVM_EXIT_HLT: + dprintf("handle_hlt\n"); + ret = kvm_handle_halt(env); + break; + } + + return ret; +}