#include "vmx.h"
#include "kvm_vmx.h"
#include <linux/module.h>
+#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/highmem.h>
+#include <linux/profile.h>
#include <asm/io.h>
#include <asm/desc.h>
#include "segment_descriptor.h"
-#define MSR_IA32_FEATURE_CONTROL 0x03a
-
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
#endif
MSR_EFER, MSR_K6_STAR,
};
-#define NR_VMX_MSR (sizeof(vmx_msr_index) / sizeof(*vmx_msr_index))
+#define NR_VMX_MSR ARRAY_SIZE(vmx_msr_index)
static inline int is_page_fault(u32 intr_info)
{
for (i = 0; i < vcpu->nmsrs; ++i)
if (vcpu->guest_msrs[i].index == msr)
return &vcpu->guest_msrs[i];
- return 0;
+ return NULL;
}
static void vmcs_clear(struct vmcs *vmcs)
static void __vcpu_clear(void *arg)
{
struct kvm_vcpu *vcpu = arg;
- int cpu = smp_processor_id();
+ int cpu = raw_smp_processor_id();
if (vcpu->cpu == cpu)
vmcs_clear(vcpu->vmcs);
per_cpu(current_vmcs, cpu) = NULL;
}
+static void vcpu_clear(struct kvm_vcpu *vcpu)
+{
+ if (vcpu->cpu != raw_smp_processor_id() && vcpu->cpu != -1)
+ smp_call_function_single(vcpu->cpu, __vcpu_clear, vcpu, 0, 1);
+ else
+ __vcpu_clear(vcpu);
+ vcpu->launched = 0;
+}
+
static unsigned long vmcs_readl(unsigned long field)
{
unsigned long value;
#endif
}
+static noinline void vmwrite_error(unsigned long field, unsigned long value)
+{
+ printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n",
+ field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
+ dump_stack();
+}
+
static void vmcs_writel(unsigned long field, unsigned long value)
{
u8 error;
asm volatile (ASM_VMX_VMWRITE_RAX_RDX "; setna %0"
: "=q"(error) : "a"(value), "d"(field) : "cc" );
- if (error)
- printk(KERN_ERR "vmwrite error: reg %lx value %lx (err %d)\n",
- field, value, vmcs_read32(VM_INSTRUCTION_ERROR));
+ if (unlikely(error))
+ vmwrite_error(field, value);
}
static void vmcs_write16(unsigned long field, u16 value)
* Switches to specified vcpu, until a matching vcpu_put(), but assumes
* vcpu mutex is already taken.
*/
-static struct kvm_vcpu *vmx_vcpu_load(struct kvm_vcpu *vcpu)
+static void vmx_vcpu_load(struct kvm_vcpu *vcpu)
{
u64 phys_addr = __pa(vcpu->vmcs);
int cpu;
cpu = get_cpu();
- if (vcpu->cpu != cpu) {
- smp_call_function(__vcpu_clear, vcpu, 0, 1);
- vcpu->launched = 0;
- }
+ if (vcpu->cpu != cpu)
+ vcpu_clear(vcpu);
if (per_cpu(current_vmcs, cpu) != vcpu->vmcs) {
u8 error;
rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
}
- return vcpu;
}
static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
put_cpu();
}
+static void vmx_vcpu_decache(struct kvm_vcpu *vcpu)
+{
+ vcpu_clear(vcpu);
+}
+
static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
{
return vmcs_readl(GUEST_RFLAGS);
if (interruptibility & 3)
vmcs_write32(GUEST_INTERRUPTIBILITY_INFO,
interruptibility & ~3);
+ vcpu->interrupt_window_open = 1;
}
static void vmx_inject_gp(struct kvm_vcpu *vcpu, unsigned error_code)
data = vmcs_readl(GUEST_GS_BASE);
break;
case MSR_EFER:
- data = vcpu->shadow_efer;
- break;
+ return kvm_get_msr_common(vcpu, msr_index, pdata);
#endif
case MSR_IA32_TIME_STAMP_COUNTER:
data = guest_read_tsc();
data = vmcs_read32(GUEST_SYSENTER_CS);
break;
case MSR_IA32_SYSENTER_EIP:
- data = vmcs_read32(GUEST_SYSENTER_EIP);
+ data = vmcs_readl(GUEST_SYSENTER_EIP);
break;
case MSR_IA32_SYSENTER_ESP:
- data = vmcs_read32(GUEST_SYSENTER_ESP);
- break;
- case MSR_IA32_MC0_CTL:
- case MSR_IA32_MCG_STATUS:
- case MSR_IA32_MCG_CAP:
- case MSR_IA32_MC0_MISC:
- case MSR_IA32_MC0_MISC+4:
- case MSR_IA32_MC0_MISC+8:
- case MSR_IA32_MC0_MISC+12:
- case MSR_IA32_MC0_MISC+16:
- case MSR_IA32_UCODE_REV:
- /* MTRR registers */
- case 0xfe:
- case 0x200 ... 0x2ff:
- data = 0;
- break;
- case MSR_IA32_APICBASE:
- data = vcpu->apic_base;
+ data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
default:
msr = find_msr_entry(vcpu, msr_index);
- if (!msr) {
- printk(KERN_ERR "kvm: unhandled rdmsr: %x\n", msr_index);
- return 1;
+ if (msr) {
+ data = msr->data;
+ break;
}
- data = msr->data;
- break;
+ return kvm_get_msr_common(vcpu, msr_index, pdata);
}
*pdata = data;
struct vmx_msr_entry *msr;
switch (msr_index) {
#ifdef CONFIG_X86_64
+ case MSR_EFER:
+ return kvm_set_msr_common(vcpu, msr_index, data);
case MSR_FS_BASE:
vmcs_writel(GUEST_FS_BASE, data);
break;
vmcs_write32(GUEST_SYSENTER_CS, data);
break;
case MSR_IA32_SYSENTER_EIP:
- vmcs_write32(GUEST_SYSENTER_EIP, data);
+ vmcs_writel(GUEST_SYSENTER_EIP, data);
break;
case MSR_IA32_SYSENTER_ESP:
- vmcs_write32(GUEST_SYSENTER_ESP, data);
+ vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
-#ifdef __x86_64
- case MSR_EFER:
- set_efer(vcpu, data);
- break;
- case MSR_IA32_MC0_STATUS:
- printk(KERN_WARNING "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n"
- , __FUNCTION__, data);
- break;
-#endif
- case MSR_IA32_TIME_STAMP_COUNTER: {
+ case MSR_IA32_TIME_STAMP_COUNTER:
guest_write_tsc(data);
break;
- }
- case MSR_IA32_UCODE_REV:
- case MSR_IA32_UCODE_WRITE:
- case 0x200 ... 0x2ff: /* MTRRs */
- break;
- case MSR_IA32_APICBASE:
- vcpu->apic_base = data;
- break;
default:
msr = find_msr_entry(vcpu, msr_index);
- if (!msr) {
- printk(KERN_ERR "kvm: unhandled wrmsr: 0x%x\n", msr_index);
- return 1;
+ if (msr) {
+ msr->data = data;
+ break;
}
+ return kvm_set_msr_common(vcpu, msr_index, data);
msr->data = data;
break;
}
return (msr & 5) == 1; /* locked but not enabled */
}
-static __init void hardware_enable(void *garbage)
+static void hardware_enable(void *garbage)
{
int cpu = raw_smp_processor_id();
u64 phys_addr = __pa(per_cpu(vmxarea, cpu));
{
u32 vmx_msr_low, vmx_msr_high;
- rdmsr(MSR_IA32_VMX_BASIC_MSR, vmx_msr_low, vmx_msr_high);
+ rdmsr(MSR_IA32_VMX_BASIC, vmx_msr_low, vmx_msr_high);
vmcs_descriptor.size = vmx_msr_high & 0x1fff;
vmcs_descriptor.order = get_order(vmcs_descriptor.size);
vmcs_descriptor.revision_id = vmx_msr_low;
-};
+}
static struct vmcs *alloc_vmcs_cpu(int cpu)
{
static struct vmcs *alloc_vmcs(void)
{
- return alloc_vmcs_cpu(smp_processor_id());
+ return alloc_vmcs_cpu(raw_smp_processor_id());
}
static void free_vmcs(struct vmcs *vmcs)
{
struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
- if (vmcs_readl(sf->base) == save->base) {
+ if (vmcs_readl(sf->base) == save->base && (save->base & AR_S_MASK)) {
vmcs_write16(sf->selector, save->selector);
vmcs_writel(sf->base, save->base);
vmcs_write32(sf->limit, save->limit);
vmcs_write32(GUEST_SS_AR_BYTES, 0xf3);
vmcs_write32(GUEST_CS_AR_BYTES, 0xf3);
+ vmcs_write32(GUEST_CS_LIMIT, 0xffff);
vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4);
fix_rmode_seg(VCPU_SREG_ES, &vcpu->rmode.es);
#endif
+static void vmx_decache_cr0_cr4_guest_bits(struct kvm_vcpu *vcpu)
+{
+ vcpu->cr0 &= KVM_GUEST_CR0_MASK;
+ vcpu->cr0 |= vmcs_readl(GUEST_CR0) & ~KVM_GUEST_CR0_MASK;
+
+ vcpu->cr4 &= KVM_GUEST_CR4_MASK;
+ vcpu->cr4 |= vmcs_readl(GUEST_CR4) & ~KVM_GUEST_CR4_MASK;
+}
+
static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
if (vcpu->rmode.active && (cr0 & CR0_PE_MASK))
*/
static void vmx_set_cr0_no_modeswitch(struct kvm_vcpu *vcpu, unsigned long cr0)
{
+ if (!vcpu->rmode.active && !(cr0 & CR0_PE_MASK))
+ enter_rmode(vcpu);
+
vcpu->rmode.active = ((cr0 & CR0_PE_MASK) == 0);
update_exception_bitmap(vcpu);
vmcs_writel(CR0_READ_SHADOW, cr0);
vmcs_write32(sf->ar_bytes, ar);
}
-static int vmx_is_long_mode(struct kvm_vcpu *vcpu)
-{
- return vmcs_read32(VM_ENTRY_CONTROLS) & VM_ENTRY_CONTROLS_IA32E_MASK;
-}
-
static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
{
u32 ar = vmcs_read32(GUEST_CS_AR_BYTES);
vmcs_writel(GUEST_RIP, 0xfff0);
vmcs_writel(GUEST_RSP, 0);
- vmcs_writel(GUEST_CR3, 0);
-
//todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0
vmcs_writel(GUEST_DR7, 0x400);
vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
/* Control */
- vmcs_write32_fixedbits(MSR_IA32_VMX_PINBASED_CTLS_MSR,
+ vmcs_write32_fixedbits(MSR_IA32_VMX_PINBASED_CTLS,
PIN_BASED_VM_EXEC_CONTROL,
PIN_BASED_EXT_INTR_MASK /* 20.6.1 */
| PIN_BASED_NMI_EXITING /* 20.6.1 */
);
- vmcs_write32_fixedbits(MSR_IA32_VMX_PROCBASED_CTLS_MSR,
+ vmcs_write32_fixedbits(MSR_IA32_VMX_PROCBASED_CTLS,
CPU_BASED_VM_EXEC_CONTROL,
CPU_BASED_HLT_EXITING /* 20.6.2 */
| CPU_BASED_CR8_LOAD_EXITING /* 20.6.2 */
| CPU_BASED_CR8_STORE_EXITING /* 20.6.2 */
| CPU_BASED_UNCOND_IO_EXITING /* 20.6.2 */
- | CPU_BASED_INVDPG_EXITING
| CPU_BASED_MOV_DR_EXITING
| CPU_BASED_USE_TSC_OFFSETING /* 21.3 */
);
rdmsrl(MSR_IA32_SYSENTER_EIP, a);
vmcs_writel(HOST_IA32_SYSENTER_EIP, a); /* 22.2.3 */
- ret = -ENOMEM;
- vcpu->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (!vcpu->guest_msrs)
- goto out;
- vcpu->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
- if (!vcpu->host_msrs)
- goto out_free_guest_msrs;
-
for (i = 0; i < NR_VMX_MSR; ++i) {
u32 index = vmx_msr_index[i];
u32 data_low, data_high;
if (rdmsr_safe(index, &data_low, &data_high) < 0)
continue;
+ if (wrmsr_safe(index, data_low, data_high) < 0)
+ continue;
data = data_low | ((u64)data_high << 32);
vcpu->host_msrs[j].index = index;
vcpu->host_msrs[j].reserved = 0;
virt_to_phys(vcpu->guest_msrs + NR_BAD_MSRS));
vmcs_writel(VM_EXIT_MSR_LOAD_ADDR,
virt_to_phys(vcpu->host_msrs + NR_BAD_MSRS));
- vmcs_write32_fixedbits(MSR_IA32_VMX_EXIT_CTLS_MSR, VM_EXIT_CONTROLS,
+ vmcs_write32_fixedbits(MSR_IA32_VMX_EXIT_CTLS, VM_EXIT_CONTROLS,
(HOST_IS_64 << 9)); /* 22.2,1, 20.7.1 */
vmcs_write32(VM_EXIT_MSR_STORE_COUNT, nr_good_msrs); /* 22.2.2 */
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, nr_good_msrs); /* 22.2.2 */
/* 22.2.1, 20.8.1 */
- vmcs_write32_fixedbits(MSR_IA32_VMX_ENTRY_CTLS_MSR,
+ vmcs_write32_fixedbits(MSR_IA32_VMX_ENTRY_CTLS,
VM_ENTRY_CONTROLS, 0);
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0); /* 22.2.1 */
return 0;
-out_free_guest_msrs:
- kfree(vcpu->guest_msrs);
out:
return ret;
}
irq | INTR_TYPE_EXT_INTR | INTR_INFO_VALID_MASK);
}
-static void kvm_try_inject_irq(struct kvm_vcpu *vcpu)
+
+static void do_interrupt_requests(struct kvm_vcpu *vcpu,
+ struct kvm_run *kvm_run)
{
- if ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF)
- && (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0)
+ u32 cpu_based_vm_exec_control;
+
+ vcpu->interrupt_window_open =
+ ((vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) &&
+ (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0);
+
+ if (vcpu->interrupt_window_open &&
+ vcpu->irq_summary &&
+ !(vmcs_read32(VM_ENTRY_INTR_INFO_FIELD) & INTR_INFO_VALID_MASK))
/*
- * Interrupts enabled, and not blocked by sti or mov ss. Good.
+ * If interrupts enabled, and not blocked by sti or mov ss. Good.
*/
kvm_do_inject_irq(vcpu);
- else
+
+ cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
+ if (!vcpu->interrupt_window_open &&
+ (vcpu->irq_summary || kvm_run->request_interrupt_window))
/*
* Interrupts blocked. Wait for unblock.
*/
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
- vmcs_read32(CPU_BASED_VM_EXEC_CONTROL)
- | CPU_BASED_VIRTUAL_INTR_PENDING);
+ cpu_based_vm_exec_control |= CPU_BASED_VIRTUAL_INTR_PENDING;
+ else
+ cpu_based_vm_exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
+ vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
}
static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu)
unsigned long cr2, rip;
u32 vect_info;
enum emulation_result er;
+ int r;
vect_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
cr2 = vmcs_readl(EXIT_QUALIFICATION);
spin_lock(&vcpu->kvm->lock);
- if (!vcpu->mmu.page_fault(vcpu, cr2, error_code)) {
+ r = kvm_mmu_page_fault(vcpu, cr2, error_code);
+ if (r < 0) {
+ spin_unlock(&vcpu->kvm->lock);
+ return r;
+ }
+ if (!r) {
spin_unlock(&vcpu->kvm->lock);
return 1;
}
return 1;
}
+static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+ return 0;
+}
static int get_io_count(struct kvm_vcpu *vcpu, u64 *count)
{
return 0;
}
-static int handle_invlpg(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void
+vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
{
- u64 address = vmcs_read64(EXIT_QUALIFICATION);
- int instruction_length = vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
- spin_lock(&vcpu->kvm->lock);
- vcpu->mmu.inval_page(vcpu, address);
- spin_unlock(&vcpu->kvm->lock);
- vmcs_writel(GUEST_RIP, vmcs_readl(GUEST_RIP) + instruction_length);
- return 1;
+ /*
+ * Patch in the VMCALL instruction:
+ */
+ hypercall[0] = 0x0f;
+ hypercall[1] = 0x01;
+ hypercall[2] = 0xc1;
+ hypercall[3] = 0xc3;
}
static int handle_cr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
return 1;
}
+static void post_kvm_run_save(struct kvm_vcpu *vcpu,
+ struct kvm_run *kvm_run)
+{
+ kvm_run->if_flag = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF) != 0;
+ kvm_run->cr8 = vcpu->cr8;
+ kvm_run->apic_base = vcpu->apic_base;
+ kvm_run->ready_for_interrupt_injection = (vcpu->interrupt_window_open &&
+ vcpu->irq_summary == 0);
+}
+
static int handle_interrupt_window(struct kvm_vcpu *vcpu,
struct kvm_run *kvm_run)
{
- /* Turn off interrupt window reporting. */
- vmcs_write32(CPU_BASED_VM_EXEC_CONTROL,
- vmcs_read32(CPU_BASED_VM_EXEC_CONTROL)
- & ~CPU_BASED_VIRTUAL_INTR_PENDING);
+ /*
+ * If the user space waits to inject interrupts, exit as soon as
+ * possible
+ */
+ if (kvm_run->request_interrupt_window &&
+ !vcpu->irq_summary) {
+ kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
+ ++kvm_stat.irq_window_exits;
+ return 0;
+ }
return 1;
}
static int handle_halt(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
skip_emulated_instruction(vcpu);
- if (vcpu->irq_summary && (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF))
+ if (vcpu->irq_summary)
return 1;
kvm_run->exit_reason = KVM_EXIT_HLT;
+ ++kvm_stat.halt_exits;
return 0;
}
+static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ vmcs_writel(GUEST_RIP, vmcs_readl(GUEST_RIP)+3);
+ return kvm_hypercall(vcpu, kvm_run);
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
struct kvm_run *kvm_run) = {
[EXIT_REASON_EXCEPTION_NMI] = handle_exception,
[EXIT_REASON_EXTERNAL_INTERRUPT] = handle_external_interrupt,
+ [EXIT_REASON_TRIPLE_FAULT] = handle_triple_fault,
[EXIT_REASON_IO_INSTRUCTION] = handle_io,
- [EXIT_REASON_INVLPG] = handle_invlpg,
[EXIT_REASON_CR_ACCESS] = handle_cr,
[EXIT_REASON_DR_ACCESS] = handle_dr,
[EXIT_REASON_CPUID] = handle_cpuid,
[EXIT_REASON_MSR_WRITE] = handle_wrmsr,
[EXIT_REASON_PENDING_INTERRUPT] = handle_interrupt_window,
[EXIT_REASON_HLT] = handle_halt,
+ [EXIT_REASON_VMCALL] = handle_vmcall,
};
static const int kvm_vmx_max_exit_handlers =
return 0;
}
+/*
+ * Check if userspace requested an interrupt window, and that the
+ * interrupt window is open.
+ *
+ * No need to exit to userspace if we already have an interrupt queued.
+ */
+static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
+ struct kvm_run *kvm_run)
+{
+ return (!vcpu->irq_summary &&
+ kvm_run->request_interrupt_window &&
+ vcpu->interrupt_window_open &&
+ (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF));
+}
+
static int vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
u8 fail;
u16 fs_sel, gs_sel, ldt_sel;
int fs_gs_ldt_reload_needed;
+ int r;
again:
/*
vmcs_writel(HOST_GS_BASE, segment_base(gs_sel));
#endif
- if (vcpu->irq_summary &&
- !(vmcs_read32(VM_ENTRY_INTR_INFO_FIELD) & INTR_INFO_VALID_MASK))
- kvm_try_inject_irq(vcpu);
+ if (!vcpu->mmio_read_completed)
+ do_interrupt_requests(vcpu, kvm_run);
if (vcpu->guest_debug.enabled)
kvm_guest_debug_pre(vcpu);
"kvm_vmx_return: "
/* Save guest registers, load host registers, keep flags */
#ifdef CONFIG_X86_64
- "xchg %3, 0(%%rsp) \n\t"
+ "xchg %3, (%%rsp) \n\t"
"mov %%rax, %c[rax](%3) \n\t"
"mov %%rbx, %c[rbx](%3) \n\t"
- "pushq 0(%%rsp); popq %c[rcx](%3) \n\t"
+ "pushq (%%rsp); popq %c[rcx](%3) \n\t"
"mov %%rdx, %c[rdx](%3) \n\t"
"mov %%rsi, %c[rsi](%3) \n\t"
"mov %%rdi, %c[rdi](%3) \n\t"
"mov %%r15, %c[r15](%3) \n\t"
"mov %%cr2, %%rax \n\t"
"mov %%rax, %c[cr2](%3) \n\t"
- "mov 0(%%rsp), %3 \n\t"
+ "mov (%%rsp), %3 \n\t"
"pop %%rcx; pop %%r15; pop %%r14; pop %%r13; pop %%r12;"
"pop %%r11; pop %%r10; pop %%r9; pop %%r8;"
"pop %%rbp; pop %%rdi; pop %%rsi;"
"pop %%rdx; pop %%rbx; pop %%rax \n\t"
#else
- "xchg %3, 0(%%esp) \n\t"
+ "xchg %3, (%%esp) \n\t"
"mov %%eax, %c[rax](%3) \n\t"
"mov %%ebx, %c[rbx](%3) \n\t"
- "pushl 0(%%esp); popl %c[rcx](%3) \n\t"
+ "pushl (%%esp); popl %c[rcx](%3) \n\t"
"mov %%edx, %c[rdx](%3) \n\t"
"mov %%esi, %c[rsi](%3) \n\t"
"mov %%edi, %c[rdi](%3) \n\t"
"mov %%ebp, %c[rbp](%3) \n\t"
"mov %%cr2, %%eax \n\t"
"mov %%eax, %c[cr2](%3) \n\t"
- "mov 0(%%esp), %3 \n\t"
+ "mov (%%esp), %3 \n\t"
"pop %%ecx; popa \n\t"
#endif
"setbe %0 \n\t"
"popf \n\t"
- : "=g" (fail)
+ : "=q" (fail)
: "r"(vcpu->launched), "d"((unsigned long)HOST_RSP),
"c"(vcpu),
[rax]"i"(offsetof(struct kvm_vcpu, regs[VCPU_REGS_RAX])),
[cr2]"i"(offsetof(struct kvm_vcpu, cr2))
: "cc", "memory" );
+ /*
+ * Reload segment selectors ASAP. (it's needed for a functional
+ * kernel: x86 relies on having __KERNEL_PDA in %fs and x86_64
+ * relies on having 0 in %gs for the CPU PDA to work.)
+ */
+ if (fs_gs_ldt_reload_needed) {
+ load_ldt(ldt_sel);
+ load_fs(fs_sel);
+ /*
+ * If we have to reload gs, we must take care to
+ * preserve our gs base.
+ */
+ local_irq_disable();
+ load_gs(gs_sel);
+#ifdef CONFIG_X86_64
+ wrmsrl(MSR_GS_BASE, vmcs_readl(HOST_GS_BASE));
+#endif
+ local_irq_enable();
+
+ reload_tss();
+ }
++kvm_stat.exits;
save_msrs(vcpu->guest_msrs, NR_BAD_MSRS);
fx_save(vcpu->guest_fx_image);
fx_restore(vcpu->host_fx_image);
+ vcpu->interrupt_window_open = (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) & 3) == 0;
-#ifndef CONFIG_X86_64
asm ("mov %0, %%ds; mov %0, %%es" : : "r"(__USER_DS));
-#endif
kvm_run->exit_type = 0;
if (fail) {
kvm_run->exit_type = KVM_EXIT_TYPE_FAIL_ENTRY;
kvm_run->exit_reason = vmcs_read32(VM_INSTRUCTION_ERROR);
+ r = 0;
} else {
- if (fs_gs_ldt_reload_needed) {
- load_ldt(ldt_sel);
- load_fs(fs_sel);
- /*
- * If we have to reload gs, we must take care to
- * preserve our gs base.
- */
- local_irq_disable();
- load_gs(gs_sel);
-#ifdef CONFIG_X86_64
- wrmsrl(MSR_GS_BASE, vmcs_readl(HOST_GS_BASE));
-#endif
- local_irq_enable();
+ /*
+ * Profile KVM exit RIPs:
+ */
+ if (unlikely(prof_on == KVM_PROFILING))
+ profile_hit(KVM_PROFILING, (void *)vmcs_readl(GUEST_RIP));
- reload_tss();
- }
vcpu->launched = 1;
kvm_run->exit_type = KVM_EXIT_TYPE_VM_EXIT;
- if (kvm_handle_exit(kvm_run, vcpu)) {
+ r = kvm_handle_exit(kvm_run, vcpu);
+ if (r > 0) {
/* Give scheduler a change to reschedule. */
if (signal_pending(current)) {
++kvm_stat.signal_exits;
+ post_kvm_run_save(vcpu, kvm_run);
+ return -EINTR;
+ }
+
+ if (dm_request_for_irq_injection(vcpu, kvm_run)) {
+ ++kvm_stat.request_irq_exits;
+ post_kvm_run_save(vcpu, kvm_run);
return -EINTR;
}
+
kvm_resched(vcpu);
goto again;
}
}
- return 0;
+
+ post_kvm_run_save(vcpu, kvm_run);
+ return r;
}
static void vmx_flush_tlb(struct kvm_vcpu *vcpu)
{
struct vmcs *vmcs;
+ vcpu->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!vcpu->guest_msrs)
+ return -ENOMEM;
+
+ vcpu->host_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
+ if (!vcpu->host_msrs)
+ goto out_free_guest_msrs;
+
vmcs = alloc_vmcs();
if (!vmcs)
- return -ENOMEM;
+ goto out_free_msrs;
+
vmcs_clear(vmcs);
vcpu->vmcs = vmcs;
vcpu->launched = 0;
+
return 0;
+
+out_free_msrs:
+ kfree(vcpu->host_msrs);
+ vcpu->host_msrs = NULL;
+
+out_free_guest_msrs:
+ kfree(vcpu->guest_msrs);
+ vcpu->guest_msrs = NULL;
+
+ return -ENOMEM;
}
static struct kvm_arch_ops vmx_arch_ops = {
.vcpu_load = vmx_vcpu_load,
.vcpu_put = vmx_vcpu_put,
+ .vcpu_decache = vmx_vcpu_decache,
.set_guest_debug = set_guest_debug,
.get_msr = vmx_get_msr,
.get_segment_base = vmx_get_segment_base,
.get_segment = vmx_get_segment,
.set_segment = vmx_set_segment,
- .is_long_mode = vmx_is_long_mode,
.get_cs_db_l_bits = vmx_get_cs_db_l_bits,
+ .decache_cr0_cr4_guest_bits = vmx_decache_cr0_cr4_guest_bits,
.set_cr0 = vmx_set_cr0,
.set_cr0_no_modeswitch = vmx_set_cr0_no_modeswitch,
.set_cr3 = vmx_set_cr3,
.run = vmx_vcpu_run,
.skip_emulated_instruction = skip_emulated_instruction,
.vcpu_setup = vmx_vcpu_setup,
+ .patch_hypercall = vmx_patch_hypercall,
};
static int __init vmx_init(void)