*/
#include <linux/kvm_host.h>
-#include "segment_descriptor.h"
#include "irq.h"
#include "mmu.h"
+#include <linux/clocksource.h>
#include <linux/kvm.h>
#include <linux/fs.h>
#include <linux/vmalloc.h>
#include <asm/uaccess.h>
#include <asm/msr.h>
+#include <asm/desc.h>
#define MAX_IO_MSRS 256
#define CR0_RESERVED_BITS \
| X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
-#define EFER_RESERVED_BITS 0xfffffffffffff2fe
+/* EFER defaults:
+ * - enable syscall per default because its emulated by KVM
+ * - enable LME and LMA per default on 64 bit KVM
+ */
+#ifdef CONFIG_X86_64
+static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffafeULL;
+#else
+static u64 __read_mostly efer_reserved_bits = 0xfffffffffffffffeULL;
+#endif
#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
{ "irq_window", VCPU_STAT(irq_window_exits) },
{ "halt_exits", VCPU_STAT(halt_exits) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
+ { "hypercalls", VCPU_STAT(hypercalls) },
{ "request_irq", VCPU_STAT(request_irq_exits) },
{ "irq_exits", VCPU_STAT(irq_exits) },
{ "host_state_reload", VCPU_STAT(host_state_reload) },
unsigned long segment_base(u16 selector)
{
struct descriptor_table gdt;
- struct segment_descriptor *d;
+ struct desc_struct *d;
unsigned long table_base;
unsigned long v;
asm("sldt %0" : "=g"(ldt_selector));
table_base = segment_base(ldt_selector);
}
- d = (struct segment_descriptor *)(table_base + (selector & ~7));
- v = d->base_low | ((unsigned long)d->base_mid << 16) |
- ((unsigned long)d->base_high << 24);
+ d = (struct desc_struct *)(table_base + (selector & ~7));
+ v = d->base0 | ((unsigned long)d->base1 << 16) |
+ ((unsigned long)d->base2 << 24);
#ifdef CONFIG_X86_64
- if (d->system == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
- v |= ((unsigned long) \
- ((struct segment_descriptor_64 *)d)->base_higher) << 32;
+ if (d->s == 0 && (d->type == 2 || d->type == 9 || d->type == 11))
+ v |= ((unsigned long)((struct ldttss_desc64 *)d)->base3) << 32;
#endif
return v;
}
return ret;
}
+EXPORT_SYMBOL_GPL(load_pdptrs);
static bool pdptrs_changed(struct kvm_vcpu *vcpu)
{
#ifdef CONFIG_X86_64
MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
- MSR_IA32_TIME_STAMP_COUNTER,
+ MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+ MSR_IA32_PERF_STATUS,
};
static unsigned num_msrs_to_save;
MSR_IA32_MISC_ENABLE,
};
-#ifdef CONFIG_X86_64
-
static void set_efer(struct kvm_vcpu *vcpu, u64 efer)
{
- if (efer & EFER_RESERVED_BITS) {
+ if (efer & efer_reserved_bits) {
printk(KERN_DEBUG "set_efer: 0x%llx #GP, reserved bits\n",
efer);
kvm_inject_gp(vcpu, 0);
vcpu->arch.shadow_efer = efer;
}
-#endif
+void kvm_enable_efer_bits(u64 mask)
+{
+ efer_reserved_bits &= ~mask;
+}
+EXPORT_SYMBOL_GPL(kvm_enable_efer_bits);
+
/*
* Writes msr value into into the appropriate "register".
return kvm_set_msr(vcpu, index, *data);
}
+static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
+{
+ static int version;
+ struct kvm_wall_clock wc;
+ struct timespec wc_ts;
+
+ if (!wall_clock)
+ return;
+
+ version++;
+
+ down_read(&kvm->slots_lock);
+ kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
+
+ wc_ts = current_kernel_time();
+ wc.wc_sec = wc_ts.tv_sec;
+ wc.wc_nsec = wc_ts.tv_nsec;
+ wc.wc_version = version;
+
+ kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));
+
+ version++;
+ kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
+ up_read(&kvm->slots_lock);
+}
+
+static void kvm_write_guest_time(struct kvm_vcpu *v)
+{
+ struct timespec ts;
+ unsigned long flags;
+ struct kvm_vcpu_arch *vcpu = &v->arch;
+ void *shared_kaddr;
+
+ if ((!vcpu->time_page))
+ return;
+
+ /* Keep irq disabled to prevent changes to the clock */
+ local_irq_save(flags);
+ kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
+ &vcpu->hv_clock.tsc_timestamp);
+ ktime_get_ts(&ts);
+ local_irq_restore(flags);
+
+ /* With all the info we got, fill in the values */
+
+ vcpu->hv_clock.system_time = ts.tv_nsec +
+ (NSEC_PER_SEC * (u64)ts.tv_sec);
+ /*
+ * The interface expects us to write an even number signaling that the
+ * update is finished. Since the guest won't see the intermediate
+ * state, we just write "2" at the end
+ */
+ vcpu->hv_clock.version = 2;
+
+ shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
+
+ memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock));
+
+ kunmap_atomic(shared_kaddr, KM_USER0);
+
+ mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
+}
+
int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
switch (msr) {
-#ifdef CONFIG_X86_64
case MSR_EFER:
set_efer(vcpu, data);
break;
-#endif
case MSR_IA32_MC0_STATUS:
pr_unimpl(vcpu, "%s: MSR_IA32_MC0_STATUS 0x%llx, nop\n",
__FUNCTION__, data);
case MSR_IA32_MISC_ENABLE:
vcpu->arch.ia32_misc_enable_msr = data;
break;
+ case MSR_KVM_WALL_CLOCK:
+ vcpu->kvm->arch.wall_clock = data;
+ kvm_write_wall_clock(vcpu->kvm, data);
+ break;
+ case MSR_KVM_SYSTEM_TIME: {
+ if (vcpu->arch.time_page) {
+ kvm_release_page_dirty(vcpu->arch.time_page);
+ vcpu->arch.time_page = NULL;
+ }
+
+ vcpu->arch.time = data;
+
+ /* we verify if the enable bit is set... */
+ if (!(data & 1))
+ break;
+
+ /* ...but clean it before doing the actual write */
+ vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
+
+ vcpu->arch.hv_clock.tsc_to_system_mul =
+ clocksource_khz2mult(tsc_khz, 22);
+ vcpu->arch.hv_clock.tsc_shift = 22;
+
+ down_read(¤t->mm->mmap_sem);
+ down_read(&vcpu->kvm->slots_lock);
+ vcpu->arch.time_page =
+ gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
+ up_read(&vcpu->kvm->slots_lock);
+ up_read(¤t->mm->mmap_sem);
+
+ if (is_error_page(vcpu->arch.time_page)) {
+ kvm_release_page_clean(vcpu->arch.time_page);
+ vcpu->arch.time_page = NULL;
+ }
+
+ kvm_write_guest_time(vcpu);
+ break;
+ }
default:
pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data);
return 1;
case MSR_IA32_MC0_MISC+12:
case MSR_IA32_MC0_MISC+16:
case MSR_IA32_UCODE_REV:
- case MSR_IA32_PERF_STATUS:
case MSR_IA32_EBL_CR_POWERON:
/* MTRR registers */
case 0xfe:
case MSR_IA32_MISC_ENABLE:
data = vcpu->arch.ia32_misc_enable_msr;
break;
-#ifdef CONFIG_X86_64
+ case MSR_IA32_PERF_STATUS:
+ /* TSC increment by tick */
+ data = 1000ULL;
+ /* CPU multiplier */
+ data |= (((uint64_t)4ULL) << 40);
+ break;
case MSR_EFER:
data = vcpu->arch.shadow_efer;
break;
-#endif
+ case MSR_KVM_WALL_CLOCK:
+ data = vcpu->kvm->arch.wall_clock;
+ break;
+ case MSR_KVM_SYSTEM_TIME:
+ data = vcpu->arch.time;
+ break;
default:
pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
return 1;
case KVM_CAP_USER_MEMORY:
case KVM_CAP_SET_TSS_ADDR:
case KVM_CAP_EXT_CPUID:
+ case KVM_CAP_CLOCKSOURCE:
r = 1;
break;
case KVM_CAP_VAPIC:
r = !kvm_x86_ops->cpu_has_accelerated_tpr();
break;
+ case KVM_CAP_NR_VCPUS:
+ r = KVM_MAX_VCPUS;
+ break;
+ case KVM_CAP_NR_MEMSLOTS:
+ r = KVM_MEMORY_SLOTS;
+ break;
default:
r = 0;
break;
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
kvm_x86_ops->vcpu_load(vcpu, cpu);
+ kvm_write_guest_time(vcpu);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
}
/* function 4 and 0xb have additional index. */
case 4: {
- int index, cache_type;
+ int i, cache_type;
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
/* read more entries until cache_type is zero */
- for (index = 1; *nent < maxnent; ++index) {
- cache_type = entry[index - 1].eax & 0x1f;
+ for (i = 1; *nent < maxnent; ++i) {
+ cache_type = entry[i - 1].eax & 0x1f;
if (!cache_type)
break;
- do_cpuid_1_ent(&entry[index], function, index);
- entry[index].flags |=
+ do_cpuid_1_ent(&entry[i], function, i);
+ entry[i].flags |=
KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
++*nent;
}
break;
}
case 0xb: {
- int index, level_type;
+ int i, level_type;
entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
/* read more entries until level_type is zero */
- for (index = 1; *nent < maxnent; ++index) {
- level_type = entry[index - 1].ecx & 0xff;
+ for (i = 1; *nent < maxnent; ++i) {
+ level_type = entry[i - 1].ecx & 0xff;
if (!level_type)
break;
- do_cpuid_1_ent(&entry[index], function, index);
- entry[index].flags |=
+ do_cpuid_1_ent(&entry[i], function, i);
+ entry[i].flags |=
KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
++*nent;
}
}
EXPORT_SYMBOL_GPL(kvm_report_emulation_failure);
-struct x86_emulate_ops emulate_ops = {
+static struct x86_emulate_ops emulate_ops = {
.read_std = emulator_read_std,
.read_emulated = emulator_read_emulated,
.write_emulated = emulator_write_emulated,
}
vcpu->arch.regs[VCPU_REGS_RAX] = ret;
kvm_x86_ops->decache_regs(vcpu);
+ ++vcpu->stat.hypercalls;
return 0;
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
static void get_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
- return kvm_x86_ops->get_segment(vcpu, var, seg);
+ kvm_x86_ops->get_segment(vcpu, var, seg);
}
void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
static void set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
- return kvm_x86_ops->set_segment(vcpu, var, seg);
+ kvm_x86_ops->set_segment(vcpu, var, seg);
}
int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
set_cr8(vcpu, sregs->cr8);
mmu_reset_needed |= vcpu->arch.shadow_efer != sregs->efer;
-#ifdef CONFIG_X86_64
kvm_x86_ops->set_efer(vcpu, sregs->efer);
-#endif
kvm_set_apic_base(vcpu, sregs->apic_base);
kvm_x86_ops->decache_cr4_guest_bits(vcpu);