static u64 construct_eptp(unsigned long root_hpa);
static void kvm_cpu_vmxon(u64 addr);
static void kvm_cpu_vmxoff(void);
+static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
static DEFINE_PER_CPU(struct vmcs *, vmxarea);
static DEFINE_PER_CPU(struct vmcs *, current_vmcs);
static unsigned long *vmx_msr_bitmap_legacy;
static unsigned long *vmx_msr_bitmap_longmode;
+static bool cpu_has_load_ia32_efer;
+
static DECLARE_BITMAP(vmx_vpid_bitmap, VMX_NR_VPIDS);
static DEFINE_SPINLOCK(vmx_vpid_lock);
u8 error;
asm volatile (__ex(ASM_VMX_VMCLEAR_RAX) "; setna %0"
- : "=g"(error) : "a"(&phys_addr), "m"(phys_addr)
+ : "=qm"(error) : "a"(&phys_addr), "m"(phys_addr)
: "cc", "memory");
if (error)
printk(KERN_ERR "kvm: vmclear fail: %p/%llx\n",
u8 error;
asm volatile (__ex(ASM_VMX_VMPTRLD_RAX) "; setna %0"
- : "=g"(error) : "a"(&phys_addr), "m"(phys_addr)
+ : "=qm"(error) : "a"(&phys_addr), "m"(phys_addr)
: "cc", "memory");
if (error)
printk(KERN_ERR "kvm: vmptrld %p/%llx fail\n",
unsigned i;
struct msr_autoload *m = &vmx->msr_autoload;
+ if (msr == MSR_EFER && cpu_has_load_ia32_efer) {
+ vmcs_clear_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER);
+ vmcs_clear_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER);
+ return;
+ }
+
for (i = 0; i < m->nr; ++i)
if (m->guest[i].index == msr)
break;
unsigned i;
struct msr_autoload *m = &vmx->msr_autoload;
+ if (msr == MSR_EFER && cpu_has_load_ia32_efer) {
+ vmcs_write64(GUEST_IA32_EFER, guest_val);
+ vmcs_write64(HOST_IA32_EFER, host_val);
+ vmcs_set_bits(VM_ENTRY_CONTROLS, VM_ENTRY_LOAD_IA32_EFER);
+ vmcs_set_bits(VM_EXIT_CONTROLS, VM_EXIT_LOAD_IA32_EFER);
+ return;
+ }
+
for (i = 0; i < m->nr; ++i)
if (m->guest[i].index == msr)
break;
return 0;
}
+static __init bool allow_1_setting(u32 msr, u32 ctl)
+{
+ u32 vmx_msr_low, vmx_msr_high;
+
+ rdmsr(msr, vmx_msr_low, vmx_msr_high);
+ return vmx_msr_high & ctl;
+}
+
static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
{
u32 vmx_msr_low, vmx_msr_high;
vmcs_conf->vmexit_ctrl = _vmexit_control;
vmcs_conf->vmentry_ctrl = _vmentry_control;
+ cpu_has_load_ia32_efer =
+ allow_1_setting(MSR_IA32_VMX_ENTRY_CTLS,
+ VM_ENTRY_LOAD_IA32_EFER)
+ && allow_1_setting(MSR_IA32_VMX_EXIT_CTLS,
+ VM_EXIT_LOAD_IA32_EFER);
+
return 0;
}
save->limit = vmcs_read32(sf->limit);
save->ar = vmcs_read32(sf->ar_bytes);
vmcs_write16(sf->selector, save->base >> 4);
- vmcs_write32(sf->base, save->base & 0xfffff);
+ vmcs_write32(sf->base, save->base & 0xffff0);
vmcs_write32(sf->limit, 0xffff);
vmcs_write32(sf->ar_bytes, 0xf3);
+ if (save->base & 0xf)
+ printk_once(KERN_WARNING "kvm: segment base is not paragraph"
+ " aligned when entering protected mode (seg=%d)",
+ seg);
}
static void enter_rmode(struct kvm_vcpu *vcpu)
vcpu->arch.cr0 |= vmcs_readl(GUEST_CR0) & cr0_guest_owned_bits;
}
+static void vmx_decache_cr3(struct kvm_vcpu *vcpu)
+{
+ if (enable_ept && is_paging(vcpu))
+ vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+}
+
static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
{
ulong cr4_guest_owned_bits = vcpu->arch.cr4_guest_owned_bits;
unsigned long cr0,
struct kvm_vcpu *vcpu)
{
+ vmx_decache_cr3(vcpu);
if (!(cr0 & X86_CR0_PG)) {
/* From paging/starting to nonpaging */
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
if (enable_ept) {
eptp = construct_eptp(cr3);
vmcs_write64(EPT_POINTER, eptp);
- guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 :
+ guest_cr3 = is_paging(vcpu) ? kvm_read_cr3(vcpu) :
vcpu->kvm->arch.ept_identity_map_addr;
ept_load_pdptrs(vcpu);
}
* Cause the #SS fault with 0 error code in VM86 mode.
*/
if (((vec == GP_VECTOR) || (vec == SS_VECTOR)) && err_code == 0)
- if (emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE)
+ if (emulate_instruction(vcpu, 0) == EMULATE_DONE)
return 1;
/*
* Forward all other exceptions that are valid in real mode.
}
if (is_invalid_opcode(intr_info)) {
- er = emulate_instruction(vcpu, 0, 0, EMULTYPE_TRAP_UD);
+ er = emulate_instruction(vcpu, EMULTYPE_TRAP_UD);
if (er != EMULATE_DONE)
kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
if (kvm_event_needs_reinjection(vcpu))
kvm_mmu_unprotect_page_virt(vcpu, cr2);
- return kvm_mmu_page_fault(vcpu, cr2, error_code);
+ return kvm_mmu_page_fault(vcpu, cr2, error_code, NULL, 0);
}
if (vmx->rmode.vm86_active &&
++vcpu->stat.io_exits;
if (string || in)
- return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
+ return emulate_instruction(vcpu, 0) == EMULATE_DONE;
port = exit_qualification >> 16;
size = (exit_qualification & 7) + 1;
hypercall[2] = 0xc1;
}
-static void complete_insn_gp(struct kvm_vcpu *vcpu, int err)
-{
- if (err)
- kvm_inject_gp(vcpu, 0);
- else
- skip_emulated_instruction(vcpu);
-}
-
static int handle_cr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification, val;
switch (cr) {
case 0:
err = kvm_set_cr0(vcpu, val);
- complete_insn_gp(vcpu, err);
+ kvm_complete_insn_gp(vcpu, err);
return 1;
case 3:
err = kvm_set_cr3(vcpu, val);
- complete_insn_gp(vcpu, err);
+ kvm_complete_insn_gp(vcpu, err);
return 1;
case 4:
err = kvm_set_cr4(vcpu, val);
- complete_insn_gp(vcpu, err);
+ kvm_complete_insn_gp(vcpu, err);
return 1;
case 8: {
u8 cr8_prev = kvm_get_cr8(vcpu);
u8 cr8 = kvm_register_read(vcpu, reg);
err = kvm_set_cr8(vcpu, cr8);
- complete_insn_gp(vcpu, err);
+ kvm_complete_insn_gp(vcpu, err);
if (irqchip_in_kernel(vcpu->kvm))
return 1;
if (cr8_prev <= cr8)
case 1: /*mov from cr*/
switch (cr) {
case 3:
- kvm_register_write(vcpu, reg, vcpu->arch.cr3);
- trace_kvm_cr_read(cr, vcpu->arch.cr3);
+ val = kvm_read_cr3(vcpu);
+ kvm_register_write(vcpu, reg, val);
+ trace_kvm_cr_read(cr, val);
skip_emulated_instruction(vcpu);
return 1;
case 8:
static int handle_invd(struct kvm_vcpu *vcpu)
{
- return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
+ return emulate_instruction(vcpu, 0) == EMULATE_DONE;
}
static int handle_invlpg(struct kvm_vcpu *vcpu)
static int handle_apic_access(struct kvm_vcpu *vcpu)
{
- return emulate_instruction(vcpu, 0, 0, 0) == EMULATE_DONE;
+ return emulate_instruction(vcpu, 0) == EMULATE_DONE;
}
static int handle_task_switch(struct kvm_vcpu *vcpu)
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
trace_kvm_page_fault(gpa, exit_qualification);
- return kvm_mmu_page_fault(vcpu, gpa, exit_qualification & 0x3);
+ return kvm_mmu_page_fault(vcpu, gpa, exit_qualification & 0x3, NULL, 0);
}
static u64 ept_rsvd_mask(u64 spte, int level)
&& (kvm_get_rflags(&vmx->vcpu) & X86_EFLAGS_IF))
return handle_interrupt_window(&vmx->vcpu);
- err = emulate_instruction(vcpu, 0, 0, 0);
+ err = emulate_instruction(vcpu, 0);
if (err == EMULATE_DO_MMIO) {
ret = 0;
if (vmx->emulation_required && emulate_invalid_guest_state)
return handle_invalid_guest_state(vcpu);
- /* Access CR3 don't cause VMExit in paging mode, so we need
- * to sync with guest real CR3. */
- if (enable_ept && is_paging(vcpu))
- vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-
if (exit_reason & VMX_EXIT_REASONS_FAILED_VMENTRY) {
vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
vcpu->run->fail_entry.hardware_entry_failure_reason
);
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
- | (1 << VCPU_EXREG_PDPTR));
+ | (1 << VCPU_EXREG_PDPTR)
+ | (1 << VCPU_EXREG_CR3));
vcpu->arch.regs_dirty = 0;
vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
.get_cpl = vmx_get_cpl,
.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
.decache_cr0_guest_bits = vmx_decache_cr0_guest_bits,
+ .decache_cr3 = vmx_decache_cr3,
.decache_cr4_guest_bits = vmx_decache_cr4_guest_bits,
.set_cr0 = vmx_set_cr0,
.set_cr3 = vmx_set_cr3,