#include <asm/mtrr.h>
#include <asm/mce.h>
#include <asm/i387.h>
+#include <asm/fpu-internal.h> /* Ugh! */
#include <asm/xcr.h>
#include <asm/pvclock.h>
#include <asm/div64.h>
struct kvm_x86_ops *kvm_x86_ops;
EXPORT_SYMBOL_GPL(kvm_x86_ops);
-int ignore_msrs = 0;
-module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR);
+static bool ignore_msrs = 0;
+module_param(ignore_msrs, bool, S_IRUGO | S_IWUSR);
bool kvm_has_tsc_control;
EXPORT_SYMBOL_GPL(kvm_has_tsc_control);
u32 kvm_max_guest_tsc_khz;
EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz);
+/* tsc tolerance in parts per million - default to 1/2 of the NTP threshold */
+static u32 tsc_tolerance_ppm = 250;
+module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR);
+
#define KVM_NR_SHARED_MSRS 16
struct kvm_shared_msrs_global {
}
EXPORT_SYMBOL_GPL(kvm_get_dr);
+bool kvm_rdpmc(struct kvm_vcpu *vcpu)
+{
+ u32 ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
+ u64 data;
+ int err;
+
+ err = kvm_pmu_read_pmc(vcpu, ecx, &data);
+ if (err)
+ return err;
+ kvm_register_write(vcpu, VCPU_REGS_RAX, (u32)data);
+ kvm_register_write(vcpu, VCPU_REGS_RDX, data >> 32);
+ return err;
+}
+EXPORT_SYMBOL_GPL(kvm_rdpmc);
+
/*
* List of msr numbers which we expose to userspace through KVM_GET_MSRS
* and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
unsigned long max_tsc_khz;
-static inline int kvm_tsc_changes_freq(void)
+static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
{
- int cpu = get_cpu();
- int ret = !boot_cpu_has(X86_FEATURE_CONSTANT_TSC) &&
- cpufreq_quick_get(cpu) != 0;
- put_cpu();
- return ret;
+ return pvclock_scale_delta(nsec, vcpu->arch.virtual_tsc_mult,
+ vcpu->arch.virtual_tsc_shift);
}
-u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu)
+static u32 adjust_tsc_khz(u32 khz, s32 ppm)
{
- if (vcpu->arch.virtual_tsc_khz)
- return vcpu->arch.virtual_tsc_khz;
- else
- return __this_cpu_read(cpu_tsc_khz);
+ u64 v = (u64)khz * (1000000 + ppm);
+ do_div(v, 1000000);
+ return v;
}
-static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
+static void kvm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
{
- u64 ret;
+ u32 thresh_lo, thresh_hi;
+ int use_scaling = 0;
- WARN_ON(preemptible());
- if (kvm_tsc_changes_freq())
- printk_once(KERN_WARNING
- "kvm: unreliable cycle conversion on adjustable rate TSC\n");
- ret = nsec * vcpu_tsc_khz(vcpu);
- do_div(ret, USEC_PER_SEC);
- return ret;
-}
-
-static void kvm_init_tsc_catchup(struct kvm_vcpu *vcpu, u32 this_tsc_khz)
-{
/* Compute a scale to convert nanoseconds in TSC cycles */
kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
- &vcpu->arch.tsc_catchup_shift,
- &vcpu->arch.tsc_catchup_mult);
+ &vcpu->arch.virtual_tsc_shift,
+ &vcpu->arch.virtual_tsc_mult);
+ vcpu->arch.virtual_tsc_khz = this_tsc_khz;
+
+ /*
+ * Compute the variation in TSC rate which is acceptable
+ * within the range of tolerance and decide if the
+ * rate being applied is within that bounds of the hardware
+ * rate. If so, no scaling or compensation need be done.
+ */
+ thresh_lo = adjust_tsc_khz(tsc_khz, -tsc_tolerance_ppm);
+ thresh_hi = adjust_tsc_khz(tsc_khz, tsc_tolerance_ppm);
+ if (this_tsc_khz < thresh_lo || this_tsc_khz > thresh_hi) {
+ pr_debug("kvm: requested TSC rate %u falls outside tolerance [%u,%u]\n", this_tsc_khz, thresh_lo, thresh_hi);
+ use_scaling = 1;
+ }
+ kvm_x86_ops->set_tsc_khz(vcpu, this_tsc_khz, use_scaling);
}
static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
{
- u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.last_tsc_nsec,
- vcpu->arch.tsc_catchup_mult,
- vcpu->arch.tsc_catchup_shift);
- tsc += vcpu->arch.last_tsc_write;
+ u64 tsc = pvclock_scale_delta(kernel_ns-vcpu->arch.this_tsc_nsec,
+ vcpu->arch.virtual_tsc_mult,
+ vcpu->arch.virtual_tsc_shift);
+ tsc += vcpu->arch.this_tsc_write;
return tsc;
}
struct kvm *kvm = vcpu->kvm;
u64 offset, ns, elapsed;
unsigned long flags;
- s64 sdiff;
+ s64 usdiff;
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
ns = get_kernel_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
- sdiff = data - kvm->arch.last_tsc_write;
- if (sdiff < 0)
- sdiff = -sdiff;
+
+ /* n.b - signed multiplication and division required */
+ usdiff = data - kvm->arch.last_tsc_write;
+#ifdef CONFIG_X86_64
+ usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
+#else
+ /* do_div() only does unsigned */
+ asm("idivl %2; xor %%edx, %%edx"
+ : "=A"(usdiff)
+ : "A"(usdiff * 1000), "rm"(vcpu->arch.virtual_tsc_khz));
+#endif
+ do_div(elapsed, 1000);
+ usdiff -= elapsed;
+ if (usdiff < 0)
+ usdiff = -usdiff;
/*
- * Special case: close write to TSC within 5 seconds of
- * another CPU is interpreted as an attempt to synchronize
- * The 5 seconds is to accommodate host load / swapping as
- * well as any reset of TSC during the boot process.
- *
- * In that case, for a reliable TSC, we can match TSC offsets,
- * or make a best guest using elapsed value.
- */
- if (sdiff < nsec_to_cycles(vcpu, 5ULL * NSEC_PER_SEC) &&
- elapsed < 5ULL * NSEC_PER_SEC) {
+ * Special case: TSC write with a small delta (1 second) of virtual
+ * cycle time against real time is interpreted as an attempt to
+ * synchronize the CPU.
+ *
+ * For a reliable TSC, we can match TSC offsets, and for an unstable
+ * TSC, we add elapsed time in this computation. We could let the
+ * compensation code attempt to catch up if we fall behind, but
+ * it's better to try to match offsets from the beginning.
+ */
+ if (usdiff < USEC_PER_SEC &&
+ vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
if (!check_tsc_unstable()) {
- offset = kvm->arch.last_tsc_offset;
+ offset = kvm->arch.cur_tsc_offset;
pr_debug("kvm: matched tsc offset for %llu\n", data);
} else {
u64 delta = nsec_to_cycles(vcpu, elapsed);
- offset += delta;
+ data += delta;
+ offset = kvm_x86_ops->compute_tsc_offset(vcpu, data);
pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
}
- ns = kvm->arch.last_tsc_nsec;
+ } else {
+ /*
+ * We split periods of matched TSC writes into generations.
+ * For each generation, we track the original measured
+ * nanosecond time, offset, and write, so if TSCs are in
+ * sync, we can match exact offset, and if not, we can match
+ * exact software computaion in compute_guest_tsc()
+ *
+ * These values are tracked in kvm->arch.cur_xxx variables.
+ */
+ kvm->arch.cur_tsc_generation++;
+ kvm->arch.cur_tsc_nsec = ns;
+ kvm->arch.cur_tsc_write = data;
+ kvm->arch.cur_tsc_offset = offset;
+ pr_debug("kvm: new tsc generation %u, clock %llu\n",
+ kvm->arch.cur_tsc_generation, data);
}
+
+ /*
+ * We also track th most recent recorded KHZ, write and time to
+ * allow the matching interval to be extended at each write.
+ */
kvm->arch.last_tsc_nsec = ns;
kvm->arch.last_tsc_write = data;
- kvm->arch.last_tsc_offset = offset;
- kvm_x86_ops->write_tsc_offset(vcpu, offset);
- raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+ kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz;
/* Reset of TSC must disable overshoot protection below */
vcpu->arch.hv_clock.tsc_timestamp = 0;
- vcpu->arch.last_tsc_write = data;
- vcpu->arch.last_tsc_nsec = ns;
+ vcpu->arch.last_guest_tsc = data;
+
+ /* Keep track of which generation this VCPU has synchronized to */
+ vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation;
+ vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
+ vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
+
+ kvm_x86_ops->write_tsc_offset(vcpu, offset);
+ raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
}
+
EXPORT_SYMBOL_GPL(kvm_write_tsc);
static int kvm_guest_time_update(struct kvm_vcpu *v)
local_irq_save(flags);
tsc_timestamp = kvm_x86_ops->read_l1_tsc(v);
kernel_ns = get_kernel_ns();
- this_tsc_khz = vcpu_tsc_khz(v);
+ this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
if (unlikely(this_tsc_khz == 0)) {
local_irq_restore(flags);
kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
if (vcpu->tsc_catchup) {
u64 tsc = compute_guest_tsc(v, kernel_ns);
if (tsc > tsc_timestamp) {
- kvm_x86_ops->adjust_tsc_offset(v, tsc - tsc_timestamp);
+ adjust_tsc_offset_guest(v, tsc - tsc_timestamp);
tsc_timestamp = tsc;
}
}
* observed by the guest and ensure the new system time is greater.
*/
max_kernel_ns = 0;
- if (vcpu->hv_clock.tsc_timestamp && vcpu->last_guest_tsc) {
+ if (vcpu->hv_clock.tsc_timestamp) {
max_kernel_ns = vcpu->last_guest_tsc -
vcpu->hv_clock.tsc_timestamp;
max_kernel_ns = pvclock_scale_delta(max_kernel_ns,
*/
vcpu->hv_clock.version += 2;
- shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
+ shared_kaddr = kmap_atomic(vcpu->time_page);
memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
sizeof(vcpu->hv_clock));
- kunmap_atomic(shared_kaddr, KM_USER0);
+ kunmap_atomic(shared_kaddr);
mark_page_dirty(v->kvm, vcpu->time >> PAGE_SHIFT);
return 0;
if (page_num >= blob_size)
goto out;
r = -ENOMEM;
- page = kzalloc(PAGE_SIZE, GFP_KERNEL);
- if (!page)
+ page = memdup_user(blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE);
+ if (IS_ERR(page)) {
+ r = PTR_ERR(page);
goto out;
- r = -EFAULT;
- if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE))
- goto out_free;
+ }
if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE))
goto out_free;
r = 0;
int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
+ bool pr = false;
+
switch (msr) {
case MSR_EFER:
return set_efer(vcpu, data);
case MSR_K7_HWCR:
data &= ~(u64)0x40; /* ignore flush filter disable */
data &= ~(u64)0x100; /* ignore ignne emulation enable */
+ data &= ~(u64)0x8; /* ignore TLB cache disable */
if (data != 0) {
pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
data);
case MSR_VM_HSAVE_PA:
case MSR_AMD64_PATCH_LOADER:
break;
+ case MSR_NHM_SNB_PKG_CST_CFG_CTL: /* 0xe2 */
case 0x200 ... 0x2ff:
return set_msr_mtrr(vcpu, msr, data);
case MSR_IA32_APICBASE:
* which we perfectly emulate ;-). Any other value should be at least
* reported, some guests depend on them.
*/
- case MSR_P6_EVNTSEL0:
- case MSR_P6_EVNTSEL1:
case MSR_K7_EVNTSEL0:
case MSR_K7_EVNTSEL1:
case MSR_K7_EVNTSEL2:
/* at least RHEL 4 unconditionally writes to the perfctr registers,
* so we ignore writes to make it happy.
*/
- case MSR_P6_PERFCTR0:
- case MSR_P6_PERFCTR1:
case MSR_K7_PERFCTR0:
case MSR_K7_PERFCTR1:
case MSR_K7_PERFCTR2:
pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
"0x%x data 0x%llx\n", msr, data);
break;
+ case MSR_P6_PERFCTR0:
+ case MSR_P6_PERFCTR1:
+ pr = true;
+ case MSR_P6_EVNTSEL0:
+ case MSR_P6_EVNTSEL1:
+ if (kvm_pmu_msr(vcpu, msr))
+ return kvm_pmu_set_msr(vcpu, msr, data);
+
+ if (pr || data != 0)
+ pr_unimpl(vcpu, "disabled perfctr wrmsr: "
+ "0x%x data 0x%llx\n", msr, data);
+ break;
case MSR_K7_CLK_CTL:
/*
* Ignore all writes to this no longer documented MSR.
*/
pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n", msr, data);
break;
+ case MSR_AMD64_OSVW_ID_LENGTH:
+ if (!guest_cpuid_has_osvw(vcpu))
+ return 1;
+ vcpu->arch.osvw.length = data;
+ break;
+ case MSR_AMD64_OSVW_STATUS:
+ if (!guest_cpuid_has_osvw(vcpu))
+ return 1;
+ vcpu->arch.osvw.status = data;
+ break;
default:
if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
return xen_hvm_config(vcpu, data);
+ if (kvm_pmu_msr(vcpu, msr))
+ return kvm_pmu_set_msr(vcpu, msr, data);
if (!ignore_msrs) {
pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
msr, data);
case MSR_K8_SYSCFG:
case MSR_K7_HWCR:
case MSR_VM_HSAVE_PA:
- case MSR_P6_PERFCTR0:
- case MSR_P6_PERFCTR1:
- case MSR_P6_EVNTSEL0:
- case MSR_P6_EVNTSEL1:
case MSR_K7_EVNTSEL0:
case MSR_K7_PERFCTR0:
case MSR_K8_INT_PENDING_MSG:
case MSR_AMD64_NB_CFG:
case MSR_FAM10H_MMIO_CONF_BASE:
+ case MSR_NHM_SNB_PKG_CST_CFG_CTL: /* 0xe2 */
+ data = 0;
+ break;
+ case MSR_P6_PERFCTR0:
+ case MSR_P6_PERFCTR1:
+ case MSR_P6_EVNTSEL0:
+ case MSR_P6_EVNTSEL1:
+ if (kvm_pmu_msr(vcpu, msr))
+ return kvm_pmu_get_msr(vcpu, msr, pdata);
data = 0;
break;
case MSR_IA32_UCODE_REV:
*/
data = 0xbe702111;
break;
+ case MSR_AMD64_OSVW_ID_LENGTH:
+ if (!guest_cpuid_has_osvw(vcpu))
+ return 1;
+ data = vcpu->arch.osvw.length;
+ break;
+ case MSR_AMD64_OSVW_STATUS:
+ if (!guest_cpuid_has_osvw(vcpu))
+ return 1;
+ data = vcpu->arch.osvw.status;
+ break;
default:
+ if (kvm_pmu_msr(vcpu, msr))
+ return kvm_pmu_get_msr(vcpu, msr, pdata);
if (!ignore_msrs) {
pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
return 1;
if (msrs.nmsrs >= MAX_IO_MSRS)
goto out;
- r = -ENOMEM;
size = sizeof(struct kvm_msr_entry) * msrs.nmsrs;
- entries = kmalloc(size, GFP_KERNEL);
- if (!entries)
+ entries = memdup_user(user_msrs->entries, size);
+ if (IS_ERR(entries)) {
+ r = PTR_ERR(entries);
goto out;
-
- r = -EFAULT;
- if (copy_from_user(entries, user_msrs->entries, size))
- goto out_free;
+ }
r = n = __msr_io(vcpu, &msrs, entries, do_msr);
if (r < 0)
case KVM_CAP_XSAVE:
case KVM_CAP_ASYNC_PF:
case KVM_CAP_GET_TSC_KHZ:
+ case KVM_CAP_PCI_2_3:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
}
kvm_x86_ops->vcpu_load(vcpu, cpu);
- if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
- /* Make sure TSC doesn't go backwards */
- s64 tsc_delta;
- u64 tsc;
- tsc = kvm_x86_ops->read_l1_tsc(vcpu);
- tsc_delta = !vcpu->arch.last_guest_tsc ? 0 :
- tsc - vcpu->arch.last_guest_tsc;
+ /* Apply any externally detected TSC adjustments (due to suspend) */
+ if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
+ adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+ vcpu->arch.tsc_offset_adjustment = 0;
+ set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ }
+ if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
+ s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
+ native_read_tsc() - vcpu->arch.last_host_tsc;
if (tsc_delta < 0)
mark_tsc_unstable("KVM discovered backwards TSC");
if (check_tsc_unstable()) {
- kvm_x86_ops->adjust_tsc_offset(vcpu, -tsc_delta);
+ u64 offset = kvm_x86_ops->compute_tsc_offset(vcpu,
+ vcpu->arch.last_guest_tsc);
+ kvm_x86_ops->write_tsc_offset(vcpu, offset);
vcpu->arch.tsc_catchup = 1;
}
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
{
kvm_x86_ops->vcpu_put(vcpu);
kvm_put_guest_fpu(vcpu);
- vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu);
+ vcpu->arch.last_host_tsc = native_read_tsc();
}
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
r = -EINVAL;
if (!vcpu->arch.apic)
goto out;
- u.lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
- r = -ENOMEM;
- if (!u.lapic)
- goto out;
- r = -EFAULT;
- if (copy_from_user(u.lapic, argp, sizeof(struct kvm_lapic_state)))
+ u.lapic = memdup_user(argp, sizeof(*u.lapic));
+ if (IS_ERR(u.lapic)) {
+ r = PTR_ERR(u.lapic);
goto out;
+ }
+
r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic);
if (r)
goto out;
break;
}
case KVM_SET_XSAVE: {
- u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL);
- r = -ENOMEM;
- if (!u.xsave)
- break;
-
- r = -EFAULT;
- if (copy_from_user(u.xsave, argp, sizeof(struct kvm_xsave)))
- break;
+ u.xsave = memdup_user(argp, sizeof(*u.xsave));
+ if (IS_ERR(u.xsave)) {
+ r = PTR_ERR(u.xsave);
+ goto out;
+ }
r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave);
break;
break;
}
case KVM_SET_XCRS: {
- u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL);
- r = -ENOMEM;
- if (!u.xcrs)
- break;
-
- r = -EFAULT;
- if (copy_from_user(u.xcrs, argp,
- sizeof(struct kvm_xcrs)))
- break;
+ u.xcrs = memdup_user(argp, sizeof(*u.xcrs));
+ if (IS_ERR(u.xcrs)) {
+ r = PTR_ERR(u.xcrs);
+ goto out;
+ }
r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs);
break;
u32 user_tsc_khz;
r = -EINVAL;
- if (!kvm_has_tsc_control)
- break;
-
user_tsc_khz = (u32)arg;
if (user_tsc_khz >= kvm_max_guest_tsc_khz)
goto out;
- kvm_x86_ops->set_tsc_khz(vcpu, user_tsc_khz);
+ if (user_tsc_khz == 0)
+ user_tsc_khz = tsc_khz;
+
+ kvm_set_tsc_khz(vcpu, user_tsc_khz);
r = 0;
goto out;
}
case KVM_GET_TSC_KHZ: {
- r = -EIO;
- if (check_tsc_unstable())
- goto out;
-
- r = vcpu_tsc_khz(vcpu);
-
+ r = vcpu->arch.virtual_tsc_khz;
goto out;
}
default:
return r;
}
+int kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
+{
+ return VM_FAULT_SIGBUS;
+}
+
static int kvm_vm_ioctl_set_tss_addr(struct kvm *kvm, unsigned long addr)
{
int ret;
unsigned long *dirty_bitmap,
unsigned long nr_dirty_pages)
{
+ spin_lock(&kvm->mmu_lock);
+
/* Not many dirty pages compared to # of shadow pages. */
if (nr_dirty_pages < kvm->arch.n_used_mmu_pages) {
unsigned long gfn_offset;
for_each_set_bit(gfn_offset, dirty_bitmap, memslot->npages) {
unsigned long gfn = memslot->base_gfn + gfn_offset;
- spin_lock(&kvm->mmu_lock);
kvm_mmu_rmap_write_protect(kvm, gfn, memslot);
- spin_unlock(&kvm->mmu_lock);
}
kvm_flush_remote_tlbs(kvm);
- } else {
- spin_lock(&kvm->mmu_lock);
+ } else
kvm_mmu_slot_remove_write_access(kvm, memslot->id);
- spin_unlock(&kvm->mmu_lock);
- }
+
+ spin_unlock(&kvm->mmu_lock);
}
/*
memset(dirty_bitmap_head, 0, n);
r = -ENOMEM;
- slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+ slots = kmemdup(kvm->memslots, sizeof(*kvm->memslots), GFP_KERNEL);
if (!slots)
goto out;
- memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
+
memslot = id_to_memslot(slots, log->slot);
memslot->nr_dirty_pages = 0;
memslot->dirty_bitmap = dirty_bitmap_head;
r = -EEXIST;
if (kvm->arch.vpic)
goto create_irqchip_unlock;
+ r = -EINVAL;
+ if (atomic_read(&kvm->online_vcpus))
+ goto create_irqchip_unlock;
r = -ENOMEM;
vpic = kvm_create_pic(kvm);
if (vpic) {
}
case KVM_GET_IRQCHIP: {
/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
- struct kvm_irqchip *chip = kmalloc(sizeof(*chip), GFP_KERNEL);
+ struct kvm_irqchip *chip;
- r = -ENOMEM;
- if (!chip)
+ chip = memdup_user(argp, sizeof(*chip));
+ if (IS_ERR(chip)) {
+ r = PTR_ERR(chip);
goto out;
- r = -EFAULT;
- if (copy_from_user(chip, argp, sizeof *chip))
- goto get_irqchip_out;
+ }
+
r = -ENXIO;
if (!irqchip_in_kernel(kvm))
goto get_irqchip_out;
}
case KVM_SET_IRQCHIP: {
/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
- struct kvm_irqchip *chip = kmalloc(sizeof(*chip), GFP_KERNEL);
+ struct kvm_irqchip *chip;
- r = -ENOMEM;
- if (!chip)
+ chip = memdup_user(argp, sizeof(*chip));
+ if (IS_ERR(chip)) {
+ r = PTR_ERR(chip);
goto out;
- r = -EFAULT;
- if (copy_from_user(chip, argp, sizeof *chip))
- goto set_irqchip_out;
+ }
+
r = -ENXIO;
if (!irqchip_in_kernel(kvm))
goto set_irqchip_out;
goto emul_write;
}
- kaddr = kmap_atomic(page, KM_USER0);
+ kaddr = kmap_atomic(page);
kaddr += offset_in_page(gpa);
switch (bytes) {
case 1:
default:
BUG();
}
- kunmap_atomic(kaddr, KM_USER0);
+ kunmap_atomic(kaddr);
kvm_release_page_dirty(page);
if (!exchanged)
return res;
}
+static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val)
+{
+ kvm_set_rflags(emul_to_vcpu(ctxt), val);
+}
+
static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt)
{
return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt));
return kvm_set_msr(emul_to_vcpu(ctxt), msr_index, data);
}
+static int emulator_read_pmc(struct x86_emulate_ctxt *ctxt,
+ u32 pmc, u64 *pdata)
+{
+ return kvm_pmu_read_pmc(emul_to_vcpu(ctxt), pmc, pdata);
+}
+
static void emulator_halt(struct x86_emulate_ctxt *ctxt)
{
emul_to_vcpu(ctxt)->arch.halt_request = 1;
return kvm_x86_ops->check_intercept(emul_to_vcpu(ctxt), info, stage);
}
+static bool emulator_get_cpuid(struct x86_emulate_ctxt *ctxt,
+ u32 *eax, u32 *ebx, u32 *ecx, u32 *edx)
+{
+ struct kvm_cpuid_entry2 *cpuid = NULL;
+
+ if (eax && ecx)
+ cpuid = kvm_find_cpuid_entry(emul_to_vcpu(ctxt),
+ *eax, *ecx);
+
+ if (cpuid) {
+ *eax = cpuid->eax;
+ *ecx = cpuid->ecx;
+ if (ebx)
+ *ebx = cpuid->ebx;
+ if (edx)
+ *edx = cpuid->edx;
+ return true;
+ }
+
+ return false;
+}
+
static struct x86_emulate_ops emulate_ops = {
.read_std = kvm_read_guest_virt_system,
.write_std = kvm_write_guest_virt_system,
.set_idt = emulator_set_idt,
.get_cr = emulator_get_cr,
.set_cr = emulator_set_cr,
+ .set_rflags = emulator_set_rflags,
.cpl = emulator_get_cpl,
.get_dr = emulator_get_dr,
.set_dr = emulator_set_dr,
.set_msr = emulator_set_msr,
.get_msr = emulator_get_msr,
+ .read_pmc = emulator_read_pmc,
.halt = emulator_halt,
.wbinvd = emulator_wbinvd,
.fix_hypercall = emulator_fix_hypercall,
.get_fpu = emulator_get_fpu,
.put_fpu = emulator_put_fpu,
.intercept = emulator_intercept,
+ .get_cpuid = emulator_get_cpuid,
};
static void cache_all_regs(struct kvm_vcpu *vcpu)
static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
-static int kvm_is_in_guest(void)
+int kvm_is_in_guest(void)
{
- return percpu_read(current_vcpu) != NULL;
+ return __this_cpu_read(current_vcpu) != NULL;
}
static int kvm_is_user_mode(void)
{
int user_mode = 3;
- if (percpu_read(current_vcpu))
- user_mode = kvm_x86_ops->get_cpl(percpu_read(current_vcpu));
+ if (__this_cpu_read(current_vcpu))
+ user_mode = kvm_x86_ops->get_cpl(__this_cpu_read(current_vcpu));
return user_mode != 0;
}
{
unsigned long ip = 0;
- if (percpu_read(current_vcpu))
- ip = kvm_rip_read(percpu_read(current_vcpu));
+ if (__this_cpu_read(current_vcpu))
+ ip = kvm_rip_read(__this_cpu_read(current_vcpu));
return ip;
}
void kvm_before_handle_nmi(struct kvm_vcpu *vcpu)
{
- percpu_write(current_vcpu, vcpu);
+ __this_cpu_write(current_vcpu, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_before_handle_nmi);
void kvm_after_handle_nmi(struct kvm_vcpu *vcpu)
{
- percpu_write(current_vcpu, NULL);
+ __this_cpu_write(current_vcpu, NULL);
}
EXPORT_SYMBOL_GPL(kvm_after_handle_nmi);
process_nmi(vcpu);
req_immediate_exit =
kvm_check_request(KVM_REQ_IMMEDIATE_EXIT, vcpu);
+ if (kvm_check_request(KVM_REQ_PMU, vcpu))
+ kvm_handle_pmu_event(vcpu);
+ if (kvm_check_request(KVM_REQ_PMI, vcpu))
+ kvm_deliver_pmi(vcpu);
}
r = kvm_mmu_reload(vcpu);
profile_hit(KVM_PROFILING, (void *)rip);
}
+ if (unlikely(vcpu->arch.tsc_always_catchup))
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
kvm_lapic_sync_from_vapic(vcpu);
return 0;
}
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
- bool has_error_code, u32 error_code)
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
+ int reason, bool has_error_code, u32 error_code)
{
struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
int ret;
init_emulate_ctxt(vcpu);
- ret = emulator_task_switch(ctxt, tss_selector, reason,
+ ret = emulator_task_switch(ctxt, tss_selector, idt_index, reason,
has_error_code, error_code);
if (ret)
kvm_async_pf_hash_reset(vcpu);
vcpu->arch.apf.halted = false;
+ kvm_pmu_reset(vcpu);
+
return kvm_x86_ops->vcpu_reset(vcpu);
}
struct kvm *kvm;
struct kvm_vcpu *vcpu;
int i;
+ int ret;
+ u64 local_tsc;
+ u64 max_tsc = 0;
+ bool stable, backwards_tsc = false;
kvm_shared_msr_cpu_online();
- list_for_each_entry(kvm, &vm_list, vm_list)
- kvm_for_each_vcpu(i, vcpu, kvm)
- if (vcpu->cpu == smp_processor_id())
- kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
- return kvm_x86_ops->hardware_enable(garbage);
+ ret = kvm_x86_ops->hardware_enable(garbage);
+ if (ret != 0)
+ return ret;
+
+ local_tsc = native_read_tsc();
+ stable = !check_tsc_unstable();
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!stable && vcpu->cpu == smp_processor_id())
+ set_bit(KVM_REQ_CLOCK_UPDATE, &vcpu->requests);
+ if (stable && vcpu->arch.last_host_tsc > local_tsc) {
+ backwards_tsc = true;
+ if (vcpu->arch.last_host_tsc > max_tsc)
+ max_tsc = vcpu->arch.last_host_tsc;
+ }
+ }
+ }
+
+ /*
+ * Sometimes, even reliable TSCs go backwards. This happens on
+ * platforms that reset TSC during suspend or hibernate actions, but
+ * maintain synchronization. We must compensate. Fortunately, we can
+ * detect that condition here, which happens early in CPU bringup,
+ * before any KVM threads can be running. Unfortunately, we can't
+ * bring the TSCs fully up to date with real time, as we aren't yet far
+ * enough into CPU bringup that we know how much real time has actually
+ * elapsed; our helper function, get_kernel_ns() will be using boot
+ * variables that haven't been updated yet.
+ *
+ * So we simply find the maximum observed TSC above, then record the
+ * adjustment to TSC in each VCPU. When the VCPU later gets loaded,
+ * the adjustment will be applied. Note that we accumulate
+ * adjustments, in case multiple suspend cycles happen before some VCPU
+ * gets a chance to run again. In the event that no KVM threads get a
+ * chance to run, we will miss the entire elapsed period, as we'll have
+ * reset last_host_tsc, so VCPUs will not have the TSC adjusted and may
+ * loose cycle time. This isn't too big a deal, since the loss will be
+ * uniform across all VCPUs (not to mention the scenario is extremely
+ * unlikely). It is possible that a second hibernate recovery happens
+ * much faster than a first, causing the observed TSC here to be
+ * smaller; this would require additional padding adjustment, which is
+ * why we set last_host_tsc to the local tsc observed here.
+ *
+ * N.B. - this code below runs only on platforms with reliable TSC,
+ * as that is the only way backwards_tsc is set above. Also note
+ * that this runs for ALL vcpus, which is not a bug; all VCPUs should
+ * have the same delta_cyc adjustment applied if backwards_tsc
+ * is detected. Note further, this adjustment is only done once,
+ * as we reset last_host_tsc on all VCPUs to stop this from being
+ * called multiple times (one for each physical CPU bringup).
+ *
+ * Platforms with unnreliable TSCs don't have to deal with this, they
+ * will be compensated by the logic in vcpu_load, which sets the TSC to
+ * catchup mode. This will catchup all VCPUs to real time, but cannot
+ * guarantee that they stay in perfect synchronization.
+ */
+ if (backwards_tsc) {
+ u64 delta_cyc = max_tsc - local_tsc;
+ list_for_each_entry(kvm, &vm_list, vm_list) {
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ vcpu->arch.tsc_offset_adjustment += delta_cyc;
+ vcpu->arch.last_host_tsc = local_tsc;
+ }
+
+ /*
+ * We have to disable TSC offset matching.. if you were
+ * booting a VM while issuing an S4 host suspend....
+ * you may have some problem. Solving this issue is
+ * left as an exercise to the reader.
+ */
+ kvm->arch.last_tsc_nsec = 0;
+ kvm->arch.last_tsc_write = 0;
+ }
+
+ }
+ return 0;
}
void kvm_arch_hardware_disable(void *garbage)
kvm_x86_ops->check_processor_compatibility(rtn);
}
+bool kvm_vcpu_compatible(struct kvm_vcpu *vcpu)
+{
+ return irqchip_in_kernel(vcpu->kvm) == (vcpu->arch.apic != NULL);
+}
+
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
struct page *page;
}
vcpu->arch.pio_data = page_address(page);
- kvm_init_tsc_catchup(vcpu, max_tsc_khz);
+ kvm_set_tsc_khz(vcpu, max_tsc_khz);
r = kvm_mmu_create(vcpu);
if (r < 0)
goto fail_free_mce_banks;
kvm_async_pf_hash_reset(vcpu);
+ kvm_pmu_init(vcpu);
return 0;
fail_free_mce_banks:
{
int idx;
+ kvm_pmu_destroy(vcpu);
kfree(vcpu->arch.mce_banks);
kvm_free_lapic(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
free_page((unsigned long)vcpu->arch.pio_data);
}
-int kvm_arch_init_vm(struct kvm *kvm)
+int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
+ if (type)
+ return -EINVAL;
+
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
put_page(kvm->arch.ept_identity_pagetable);
}
+void kvm_arch_free_memslot(struct kvm_memory_slot *free,
+ struct kvm_memory_slot *dont)
+{
+ int i;
+
+ for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+ if (!dont || free->arch.lpage_info[i] != dont->arch.lpage_info[i]) {
+ vfree(free->arch.lpage_info[i]);
+ free->arch.lpage_info[i] = NULL;
+ }
+ }
+}
+
+int kvm_arch_create_memslot(struct kvm_memory_slot *slot, unsigned long npages)
+{
+ int i;
+
+ for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+ unsigned long ugfn;
+ int lpages;
+ int level = i + 2;
+
+ lpages = gfn_to_index(slot->base_gfn + npages - 1,
+ slot->base_gfn, level) + 1;
+
+ slot->arch.lpage_info[i] =
+ vzalloc(lpages * sizeof(*slot->arch.lpage_info[i]));
+ if (!slot->arch.lpage_info[i])
+ goto out_free;
+
+ if (slot->base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1))
+ slot->arch.lpage_info[i][0].write_count = 1;
+ if ((slot->base_gfn + npages) & (KVM_PAGES_PER_HPAGE(level) - 1))
+ slot->arch.lpage_info[i][lpages - 1].write_count = 1;
+ ugfn = slot->userspace_addr >> PAGE_SHIFT;
+ /*
+ * If the gfn and userspace address are not aligned wrt each
+ * other, or if explicitly asked to, disable large page
+ * support for this slot
+ */
+ if ((slot->base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) ||
+ !kvm_largepages_enabled()) {
+ unsigned long j;
+
+ for (j = 0; j < lpages; ++j)
+ slot->arch.lpage_info[i][j].write_count = 1;
+ }
+ }
+
+ return 0;
+
+out_free:
+ for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) {
+ vfree(slot->arch.lpage_info[i]);
+ slot->arch.lpage_info[i] = NULL;
+ }
+ return -ENOMEM;
+}
+
int kvm_arch_prepare_memory_region(struct kvm *kvm,
struct kvm_memory_slot *memslot,
struct kvm_memory_slot old,
if (npages && !old.rmap) {
unsigned long userspace_addr;
- down_write(¤t->mm->mmap_sem);
- userspace_addr = do_mmap(NULL, 0,
+ userspace_addr = vm_mmap(NULL, 0,
npages * PAGE_SIZE,
PROT_READ | PROT_WRITE,
map_flags,
0);
- up_write(¤t->mm->mmap_sem);
if (IS_ERR((void *)userspace_addr))
return PTR_ERR((void *)userspace_addr);
if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
int ret;
- down_write(¤t->mm->mmap_sem);
- ret = do_munmap(current->mm, old.userspace_addr,
+ ret = vm_munmap(old.userspace_addr,
old.npages * PAGE_SIZE);
- up_write(¤t->mm->mmap_sem);
if (ret < 0)
printk(KERN_WARNING
"kvm_vm_ioctl_set_memory_region: "
kvm_inject_page_fault(vcpu, &fault);
}
vcpu->arch.apf.halted = false;
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
}
bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)