int ret;
u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];
- down_read(&vcpu->kvm->slots_lock);
ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte,
offset * sizeof(u64), sizeof(pdpte));
if (ret < 0) {
memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs));
out:
- up_read(&vcpu->kvm->slots_lock);
return ret;
}
if (is_long_mode(vcpu) || !is_pae(vcpu))
return false;
- down_read(&vcpu->kvm->slots_lock);
r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte));
if (r < 0)
goto out;
changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0;
out:
- up_read(&vcpu->kvm->slots_lock);
return changed;
}
void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
{
kvm_set_cr0(vcpu, (vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f));
+ KVMTRACE_1D(LMSW, vcpu,
+ (u32)((vcpu->arch.cr0 & ~0x0ful) | (msw & 0x0f)),
+ handler);
}
EXPORT_SYMBOL_GPL(kvm_lmsw);
*/
}
- down_read(&vcpu->kvm->slots_lock);
/*
* Does the new cr3 value map to physical memory? (Note, we
* catch an invalid cr3 even in real-mode, because it would
vcpu->arch.cr3 = cr3;
vcpu->arch.mmu.new_cr3(vcpu);
}
- up_read(&vcpu->kvm->slots_lock);
}
EXPORT_SYMBOL_GPL(kvm_set_cr3);
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;
+ struct pvclock_wall_clock wc;
+ struct timespec now, sys, boot;
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;
+ /*
+ * The guest calculates current wall clock time by adding
+ * system time (updated by kvm_write_guest_time below) to the
+ * wall clock specified here. guest system time equals host
+ * system time for us, thus we must fill in host boot time here.
+ */
+ now = current_kernel_time();
+ ktime_get_ts(&sys);
+ boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys));
+
+ wc.sec = boot.tv_sec;
+ wc.nsec = boot.tv_nsec;
+ 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 uint32_t div_frac(uint32_t dividend, uint32_t divisor)
+{
+ uint32_t quotient, remainder;
+
+ /* Don't try to replace with do_div(), this one calculates
+ * "(dividend << 32) / divisor" */
+ __asm__ ( "divl %4"
+ : "=a" (quotient), "=d" (remainder)
+ : "0" (0), "1" (dividend), "r" (divisor) );
+ return quotient;
+}
+
+static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
+{
+ uint64_t nsecs = 1000000000LL;
+ int32_t shift = 0;
+ uint64_t tps64;
+ uint32_t tps32;
+
+ tps64 = tsc_khz * 1000LL;
+ while (tps64 > nsecs*2) {
+ tps64 >>= 1;
+ shift--;
+ }
+
+ tps32 = (uint32_t)tps64;
+ while (tps32 <= (uint32_t)nsecs) {
+ tps32 <<= 1;
+ shift++;
+ }
+
+ hv_clock->tsc_shift = shift;
+ hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);
+
+ pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n",
+ __FUNCTION__, tsc_khz, hv_clock->tsc_shift,
+ hv_clock->tsc_to_system_mul);
}
static void kvm_write_guest_time(struct kvm_vcpu *v)
if ((!vcpu->time_page))
return;
+ if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) {
+ kvm_set_time_scale(tsc_khz, &vcpu->hv_clock);
+ vcpu->hv_clock_tsc_khz = tsc_khz;
+ }
+
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
/*
* 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
+ * state, we just increase by 2 at the end.
*/
- vcpu->hv_clock.version = 2;
+ 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));
+ sizeof(vcpu->hv_clock));
kunmap_atomic(shared_kaddr, KM_USER0);
/* ...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)) {
vcpu_load(vcpu);
+ down_read(&vcpu->kvm->slots_lock);
for (i = 0; i < msrs->nmsrs; ++i)
if (do_msr(vcpu, entries[i].index, &entries[i].data))
break;
+ up_read(&vcpu->kvm->slots_lock);
vcpu_put(vcpu);
case KVM_CAP_CLOCKSOURCE:
case KVM_CAP_PIT:
case KVM_CAP_NOP_IO_DELAY:
+ case KVM_CAP_MP_STATE:
r = 1;
break;
case KVM_CAP_VAPIC:
void *data = val;
int r = X86EMUL_CONTINUE;
- down_read(&vcpu->kvm->slots_lock);
while (bytes) {
gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
unsigned offset = addr & (PAGE_SIZE-1);
addr += tocopy;
}
out:
- up_read(&vcpu->kvm->slots_lock);
return r;
}
EXPORT_SYMBOL_GPL(emulator_read_std);
return X86EMUL_CONTINUE;
}
- down_read(&vcpu->kvm->slots_lock);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
- up_read(&vcpu->kvm->slots_lock);
/* For APIC access vmexit */
if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
return X86EMUL_UNHANDLEABLE;
}
-int __emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
+int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
const void *val, int bytes)
{
int ret;
return 1;
}
-static int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
- const void *val, int bytes)
-{
- int ret;
-
- down_read(&vcpu->kvm->slots_lock);
- ret =__emulator_write_phys(vcpu, gpa, val, bytes);
- up_read(&vcpu->kvm->slots_lock);
- return ret;
-}
-
static int emulator_write_emulated_onepage(unsigned long addr,
const void *val,
unsigned int bytes,
struct kvm_io_device *mmio_dev;
gpa_t gpa;
- down_read(&vcpu->kvm->slots_lock);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
- up_read(&vcpu->kvm->slots_lock);
if (gpa == UNMAPPED_GVA) {
kvm_inject_page_fault(vcpu, addr, 2);
char *kaddr;
u64 val;
- down_read(&vcpu->kvm->slots_lock);
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr);
if (gpa == UNMAPPED_GVA ||
set_64bit((u64 *)(kaddr + offset_in_page(gpa)), val);
kunmap_atomic(kaddr, KM_USER0);
kvm_release_page_dirty(page);
- emul_write:
- up_read(&vcpu->kvm->slots_lock);
}
+emul_write:
#endif
return emulator_write_emulated(addr, new, bytes, vcpu);
vcpu->arch.pio.guest_page_offset = 0;
vcpu->arch.pio.rep = 0;
+ if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
+ KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
+ handler);
+ else
+ KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
+ handler);
+
kvm_x86_ops->cache_regs(vcpu);
memcpy(vcpu->arch.pio_data, &vcpu->arch.regs[VCPU_REGS_RAX], 4);
kvm_x86_ops->decache_regs(vcpu);
vcpu->arch.pio.guest_page_offset = offset_in_page(address);
vcpu->arch.pio.rep = rep;
+ if (vcpu->run->io.direction == KVM_EXIT_IO_IN)
+ KVMTRACE_2D(IO_READ, vcpu, vcpu->run->io.port, (u32)size,
+ handler);
+ else
+ KVMTRACE_2D(IO_WRITE, vcpu, vcpu->run->io.port, (u32)size,
+ handler);
+
if (!count) {
kvm_x86_ops->skip_emulated_instruction(vcpu);
return 1;
kvm_x86_ops->skip_emulated_instruction(vcpu);
for (i = 0; i < nr_pages; ++i) {
- down_read(&vcpu->kvm->slots_lock);
page = gva_to_page(vcpu, address + i * PAGE_SIZE);
vcpu->arch.pio.guest_pages[i] = page;
- up_read(&vcpu->kvm->slots_lock);
if (!page) {
kvm_inject_gp(vcpu, 0);
free_pio_guest_pages(vcpu);
kvm_x86_ops = ops;
kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
+ kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
+ kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
+ PT_DIRTY_MASK, PT64_NX_MASK, 0);
return 0;
out:
int kvm_emulate_halt(struct kvm_vcpu *vcpu)
{
++vcpu->stat.halt_exits;
+ KVMTRACE_0D(HLT, vcpu, handler);
if (irqchip_in_kernel(vcpu->kvm)) {
- vcpu->arch.mp_state = VCPU_MP_STATE_HALTED;
+ vcpu->arch.mp_state = KVM_MP_STATE_HALTED;
+ up_read(&vcpu->kvm->slots_lock);
kvm_vcpu_block(vcpu);
- if (vcpu->arch.mp_state != VCPU_MP_STATE_RUNNABLE)
+ down_read(&vcpu->kvm->slots_lock);
+ if (vcpu->arch.mp_state != KVM_MP_STATE_RUNNABLE)
return -EINTR;
return 1;
} else {
a2 = vcpu->arch.regs[VCPU_REGS_RDX];
a3 = vcpu->arch.regs[VCPU_REGS_RSI];
+ KVMTRACE_1D(VMMCALL, vcpu, (u32)nr, handler);
+
if (!is_long_mode(vcpu)) {
nr &= 0xFFFFFFFF;
a0 &= 0xFFFFFFFF;
}
kvm_x86_ops->decache_regs(vcpu);
kvm_x86_ops->skip_emulated_instruction(vcpu);
+ KVMTRACE_5D(CPUID, vcpu, function,
+ (u32)vcpu->arch.regs[VCPU_REGS_RAX],
+ (u32)vcpu->arch.regs[VCPU_REGS_RBX],
+ (u32)vcpu->arch.regs[VCPU_REGS_RCX],
+ (u32)vcpu->arch.regs[VCPU_REGS_RDX], handler);
}
EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
{
int r;
- if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED)) {
+ if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED)) {
pr_debug("vcpu %d received sipi with vector # %x\n",
vcpu->vcpu_id, vcpu->arch.sipi_vector);
kvm_lapic_reset(vcpu);
r = kvm_x86_ops->vcpu_reset(vcpu);
if (r)
return r;
- vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
}
+ down_read(&vcpu->kvm->slots_lock);
vapic_enter(vcpu);
preempted:
if (vcpu->requests) {
if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
- __kvm_migrate_apic_timer(vcpu);
+ __kvm_migrate_timers(vcpu);
+ if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+ kvm_x86_ops->tlb_flush(vcpu);
if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
&vcpu->requests)) {
kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
}
}
+ clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
kvm_inject_pending_timer_irqs(vcpu);
preempt_disable();
local_irq_disable();
- if (need_resched()) {
+ if (vcpu->requests || need_resched()) {
local_irq_enable();
preempt_enable();
r = 1;
goto out;
}
- if (vcpu->requests)
- if (test_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) {
- local_irq_enable();
- preempt_enable();
- r = 1;
- goto out;
- }
-
if (signal_pending(current)) {
local_irq_enable();
preempt_enable();
goto out;
}
+ vcpu->guest_mode = 1;
+ /*
+ * Make sure that guest_mode assignment won't happen after
+ * testing the pending IRQ vector bitmap.
+ */
+ smp_wmb();
+
if (vcpu->arch.exception.pending)
__queue_exception(vcpu);
else if (irqchip_in_kernel(vcpu->kvm))
kvm_lapic_sync_to_vapic(vcpu);
- vcpu->guest_mode = 1;
+ up_read(&vcpu->kvm->slots_lock);
+
kvm_guest_enter();
- if (vcpu->requests)
- if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
- kvm_x86_ops->tlb_flush(vcpu);
+ KVMTRACE_0D(VMENTRY, vcpu, entryexit);
kvm_x86_ops->run(vcpu, kvm_run);
vcpu->guest_mode = 0;
preempt_enable();
+ down_read(&vcpu->kvm->slots_lock);
+
/*
* Profile KVM exit RIPs:
*/
}
out:
+ up_read(&vcpu->kvm->slots_lock);
if (r > 0) {
kvm_resched(vcpu);
+ down_read(&vcpu->kvm->slots_lock);
goto preempted;
}
post_kvm_run_save(vcpu, kvm_run);
+ down_read(&vcpu->kvm->slots_lock);
vapic_exit(vcpu);
+ up_read(&vcpu->kvm->slots_lock);
return r;
}
vcpu_load(vcpu);
- if (unlikely(vcpu->arch.mp_state == VCPU_MP_STATE_UNINITIALIZED)) {
+ if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
kvm_vcpu_block(vcpu);
vcpu_put(vcpu);
return -EAGAIN;
memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
vcpu->mmio_read_completed = 1;
vcpu->mmio_needed = 0;
+
+ down_read(&vcpu->kvm->slots_lock);
r = emulate_instruction(vcpu, kvm_run,
vcpu->arch.mmio_fault_cr2, 0,
EMULTYPE_NO_DECODE);
+ up_read(&vcpu->kvm->slots_lock);
if (r == EMULATE_DO_MMIO) {
/*
* Read-modify-write. Back to userspace.
kvm_x86_ops->decache_regs(vcpu);
+ vcpu->arch.exception.pending = false;
+
vcpu_put(vcpu);
return 0;
return 0;
}
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ vcpu_load(vcpu);
+ mp_state->mp_state = vcpu->arch.mp_state;
+ vcpu_put(vcpu);
+ return 0;
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ vcpu_load(vcpu);
+ vcpu->arch.mp_state = mp_state->mp_state;
+ vcpu_put(vcpu);
+ return 0;
+}
+
static void set_segment(struct kvm_vcpu *vcpu,
struct kvm_segment *var, int seg)
{
}
if (reason == TASK_SWITCH_IRET || reason == TASK_SWITCH_JMP) {
- cseg_desc.type &= ~(1 << 8); //clear the B flag
+ cseg_desc.type &= ~(1 << 1); //clear the B flag
save_guest_segment_descriptor(vcpu, tr_seg.selector,
&cseg_desc);
}
}
if (reason != TASK_SWITCH_IRET) {
- nseg_desc.type |= (1 << 8);
+ nseg_desc.type |= (1 << 1);
save_guest_segment_descriptor(vcpu, tss_selector,
&nseg_desc);
}
{
unsigned after_mxcsr_mask;
+ /*
+ * Touch the fpu the first time in non atomic context as if
+ * this is the first fpu instruction the exception handler
+ * will fire before the instruction returns and it'll have to
+ * allocate ram with GFP_KERNEL.
+ */
+ if (!used_math())
+ fx_save(&vcpu->arch.host_fx_image);
+
/* Initialize guest FPU by resetting ours and saving into guest's */
preempt_disable();
fx_save(&vcpu->arch.host_fx_image);
- fpu_init();
+ fx_finit();
fx_save(&vcpu->arch.guest_fx_image);
fx_restore(&vcpu->arch.host_fx_image);
preempt_enable();
vcpu->arch.mmu.root_hpa = INVALID_PAGE;
if (!irqchip_in_kernel(kvm) || vcpu->vcpu_id == 0)
- vcpu->arch.mp_state = VCPU_MP_STATE_RUNNABLE;
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
else
- vcpu->arch.mp_state = VCPU_MP_STATE_UNINITIALIZED;
+ vcpu->arch.mp_state = KVM_MP_STATE_UNINITIALIZED;
page = alloc_page(GFP_KERNEL | __GFP_ZERO);
if (!page) {
void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
kvm_free_lapic(vcpu);
+ down_read(&vcpu->kvm->slots_lock);
kvm_mmu_destroy(vcpu);
+ up_read(&vcpu->kvm->slots_lock);
free_page((unsigned long)vcpu->arch.pio_data);
}
kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
kvm_free_physmem(kvm);
+ if (kvm->arch.apic_access_page)
+ put_page(kvm->arch.apic_access_page);
+ if (kvm->arch.ept_identity_pagetable)
+ put_page(kvm->arch.ept_identity_pagetable);
kfree(kvm);
}
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.mp_state == VCPU_MP_STATE_RUNNABLE
- || vcpu->arch.mp_state == VCPU_MP_STATE_SIPI_RECEIVED;
+ return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
+ || vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED;
}
static void vcpu_kick_intr(void *info)
void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
{
int ipi_pcpu = vcpu->cpu;
+ int cpu = get_cpu();
if (waitqueue_active(&vcpu->wq)) {
wake_up_interruptible(&vcpu->wq);
++vcpu->stat.halt_wakeup;
}
- if (vcpu->guest_mode)
+ /*
+ * We may be called synchronously with irqs disabled in guest mode,
+ * So need not to call smp_call_function_single() in that case.
+ */
+ if (vcpu->guest_mode && vcpu->cpu != cpu)
smp_call_function_single(ipi_pcpu, vcpu_kick_intr, vcpu, 0, 0);
+ put_cpu();
}