#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"
-
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)
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);
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);
+ data = vmcs_readl(GUEST_SYSENTER_ESP);
break;
default:
msr = find_msr_entry(vcpu, msr_index);
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;
- case MSR_IA32_TIME_STAMP_COUNTER: {
+ case MSR_IA32_TIME_STAMP_COUNTER:
guest_write_tsc(data);
break;
- }
default:
msr = find_msr_entry(vcpu, msr_index);
if (msr) {
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));
{
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_CS_AR_BYTES, 0xf3);
vmcs_write32(GUEST_CS_LIMIT, 0xffff);
+ if (vmcs_readl(GUEST_CS_BASE) == 0xffff0000)
+ vmcs_writel(GUEST_CS_BASE, 0xf0000);
vmcs_write16(GUEST_CS_SELECTOR, vmcs_readl(GUEST_CS_BASE) >> 4);
fix_rmode_seg(VCPU_SREG_ES, &vcpu->rmode.es);
vcpu->cr0 = cr0;
}
-/*
- * Used when restoring the VM to avoid corrupting segment registers
- */
-static void vmx_set_cr0_no_modeswitch(struct kvm_vcpu *vcpu, unsigned long cr0)
-{
- vcpu->rmode.active = ((cr0 & CR0_PE_MASK) == 0);
- update_exception_bitmap(vcpu);
- vmcs_writel(CR0_READ_SHADOW, cr0);
- vmcs_writel(GUEST_CR0,
- (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON);
- vcpu->cr0 = cr0;
-}
-
static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
vmcs_writel(GUEST_CR3, cr3);
vmcs_writel(sf->base, var->base);
vmcs_write32(sf->limit, var->limit);
vmcs_write16(sf->selector, var->selector);
- if (var->unusable)
+ if (vcpu->rmode.active && var->s) {
+ /*
+ * Hack real-mode segments into vm86 compatibility.
+ */
+ if (var->base == 0xffff0000 && var->selector == 0xf000)
+ vmcs_writel(sf->base, 0xf0000);
+ ar = 0xf3;
+ } else if (var->unusable)
ar = 1 << 16;
else {
ar = var->type & 15;
gfn_t fn = rmode_tss_base(kvm) >> PAGE_SHIFT;
char *page;
- p1 = _gfn_to_page(kvm, fn++);
- p2 = _gfn_to_page(kvm, fn++);
- p3 = _gfn_to_page(kvm, fn);
+ p1 = gfn_to_page(kvm, fn++);
+ p2 = gfn_to_page(kvm, fn++);
+ p3 = gfn_to_page(kvm, fn);
if (!p1 || !p2 || !p3) {
kvm_printf(kvm,"%s: gfn_to_page failed\n", __FUNCTION__);
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);
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;
vcpu->guest_msrs[j] = vcpu->host_msrs[j];
++vcpu->nmsrs;
}
- printk(KERN_DEBUG "kvm: msrs: %d\n", vcpu->nmsrs);
nr_good_msrs = vcpu->nmsrs - NR_BAD_MSRS;
vmcs_writel(VM_ENTRY_MSR_LOAD_ADDR,
u16 sp = vmcs_readl(GUEST_RSP);
u32 ss_limit = vmcs_read32(GUEST_SS_LIMIT);
- if (sp > ss_limit || sp - 6 > sp) {
+ if (sp > ss_limit || sp < 6 ) {
vcpu_printf(vcpu, "%s: #SS, rsp 0x%lx ss 0x%lx limit 0x%x\n",
__FUNCTION__,
vmcs_readl(GUEST_RSP),
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)
+static int get_io_count(struct kvm_vcpu *vcpu, unsigned long *count)
{
u64 inst;
gva_t rip;
done:
countr_size *= 8;
*count = vcpu->regs[VCPU_REGS_RCX] & (~0ULL >> (64 - countr_size));
+ //printk("cx: %lx\n", vcpu->regs[VCPU_REGS_RCX]);
return 1;
}
static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
u64 exit_qualification;
+ int size, down, in, string, rep;
+ unsigned port;
+ unsigned long count;
+ gva_t address;
++kvm_stat.io_exits;
exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
- kvm_run->exit_reason = KVM_EXIT_IO;
- if (exit_qualification & 8)
- kvm_run->io.direction = KVM_EXIT_IO_IN;
- else
- kvm_run->io.direction = KVM_EXIT_IO_OUT;
- kvm_run->io.size = (exit_qualification & 7) + 1;
- kvm_run->io.string = (exit_qualification & 16) != 0;
- kvm_run->io.string_down
- = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0;
- kvm_run->io.rep = (exit_qualification & 32) != 0;
- kvm_run->io.port = exit_qualification >> 16;
- if (kvm_run->io.string) {
- if (!get_io_count(vcpu, &kvm_run->io.count))
+ in = (exit_qualification & 8) != 0;
+ size = (exit_qualification & 7) + 1;
+ string = (exit_qualification & 16) != 0;
+ down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0;
+ count = 1;
+ rep = (exit_qualification & 32) != 0;
+ port = exit_qualification >> 16;
+ address = 0;
+ if (string) {
+ if (rep && !get_io_count(vcpu, &count))
return 1;
- kvm_run->io.address = vmcs_readl(GUEST_LINEAR_ADDRESS);
- } else
- kvm_run->io.value = vcpu->regs[VCPU_REGS_RAX]; /* rax */
- return 0;
+ address = vmcs_readl(GUEST_LINEAR_ADDRESS);
+ }
+ return kvm_setup_pio(vcpu, kvm_run, in, size, count, string, down,
+ address, rep, port);
+}
+
+static void
+vmx_patch_hypercall(struct kvm_vcpu *vcpu, unsigned char *hypercall)
+{
+ /*
+ * 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)
static int handle_cpuid(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
{
- kvm_run->exit_reason = KVM_EXIT_CPUID;
- return 0;
+ kvm_emulate_cpuid(vcpu);
+ return 1;
}
static int handle_rdmsr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
* possible
*/
if (kvm_run->request_interrupt_window &&
- !vcpu->irq_summary &&
- (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_IF)) {
+ !vcpu->irq_summary) {
kvm_run->exit_reason = KVM_EXIT_IRQ_WINDOW_OPEN;
++kvm_stat.irq_window_exits;
return 0;
return 0;
}
+static int handle_vmcall(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+ skip_emulated_instruction(vcpu);
+ 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_CR_ACCESS] = handle_cr,
[EXIT_REASON_DR_ACCESS] = handle_dr,
[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 =
vmcs_writel(HOST_GS_BASE, segment_base(gs_sel));
#endif
- do_interrupt_requests(vcpu, kvm_run);
+ 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_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);
+ kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ kvm_run->fail_entry.hardware_entry_failure_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;
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);
+ kvm_run->exit_reason = KVM_EXIT_INTR;
return -EINTR;
}
if (dm_request_for_irq_injection(vcpu, kvm_run)) {
++kvm_stat.request_irq_exits;
post_kvm_run_save(vcpu, kvm_run);
+ kvm_run->exit_reason = KVM_EXIT_INTR;
return -EINTR;
}
.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_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,
.set_cr4 = vmx_set_cr4,
#ifdef CONFIG_X86_64
.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)