#include "tss.h"
#include "kvm_cache_regs.h"
#include "x86.h"
+#include "cpuid.h"
#include <linux/clocksource.h>
#include <linux/interrupt.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
#include <linux/hash.h>
+#include <linux/pci.h>
#include <trace/events/kvm.h>
#define CREATE_TRACE_POINTS
#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>
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
static void update_cr8_intercept(struct kvm_vcpu *vcpu);
-static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries);
+static void process_nmi(struct kvm_vcpu *vcpu);
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 {
void kvm_inject_nmi(struct kvm_vcpu *vcpu)
{
- kvm_make_request(KVM_REQ_EVENT, vcpu);
- vcpu->arch.nmi_pending = 1;
+ atomic_inc(&vcpu->arch.nmi_queued);
+ kvm_make_request(KVM_REQ_NMI, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_inject_nmi);
}
EXPORT_SYMBOL_GPL(kvm_set_xcr);
-static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- return best && (best->ecx & bit(X86_FEATURE_XSAVE));
-}
-
-static bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_SMEP));
-}
-
-static bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 7, 0);
- return best && (best->ebx & bit(X86_FEATURE_FSGSBASE));
-}
-
-static void update_cpuid(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 1, 0);
- if (!best)
- return;
-
- /* Update OSXSAVE bit */
- if (cpu_has_xsave && best->function == 0x1) {
- best->ecx &= ~(bit(X86_FEATURE_OSXSAVE));
- if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE))
- best->ecx |= bit(X86_FEATURE_OSXSAVE);
- }
-}
-
int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
{
unsigned long old_cr4 = kvm_read_cr4(vcpu);
kvm_mmu_reset_context(vcpu);
if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
- update_cpuid(vcpu);
+ kvm_update_cpuid(vcpu);
return 0;
}
}
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 unsigned num_msrs_to_save;
static u32 emulated_msrs[] = {
+ MSR_IA32_TSCDEADLINE,
MSR_IA32_MISC_ENABLE,
MSR_IA32_MCG_STATUS,
MSR_IA32_MCG_CTL,
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);
}
-static 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)
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
- kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
+ 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 0xe2:
+ case MSR_NHM_SNB_PKG_CST_CFG_CTL: /* 0xe2 */
case 0x200 ... 0x2ff:
return set_msr_mtrr(vcpu, msr, data);
case MSR_IA32_APICBASE:
break;
case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
return kvm_x2apic_msr_write(vcpu, msr, data);
+ case MSR_IA32_TSCDEADLINE:
+ kvm_set_lapic_tscdeadline_msr(vcpu, data);
+ break;
case MSR_IA32_MISC_ENABLE:
vcpu->arch.ia32_misc_enable_msr = data;
break;
* 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);
return kvm_hv_vapic_msr_read(vcpu, APIC_ICR, pdata);
case HV_X64_MSR_TPR:
return kvm_hv_vapic_msr_read(vcpu, APIC_TASKPRI, pdata);
+ case HV_X64_MSR_APIC_ASSIST_PAGE:
+ data = vcpu->arch.hv_vapic;
+ break;
default:
pr_unimpl(vcpu, "Hyper-V unhandled rdmsr: 0x%x\n", msr);
return 1;
switch (msr) {
case MSR_IA32_PLATFORM_ID:
- case MSR_IA32_UCODE_REV:
case MSR_IA32_EBL_CR_POWERON:
case MSR_IA32_DEBUGCTLMSR:
case MSR_IA32_LASTBRANCHFROMIP:
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 0xe2:
+ 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 = 0x100000000ULL;
+ break;
case MSR_MTRRcap:
data = 0x500 | KVM_NR_VAR_MTRR;
break;
case APIC_BASE_MSR ... APIC_BASE_MSR + 0x3ff:
return kvm_x2apic_msr_read(vcpu, msr, pdata);
break;
+ case MSR_IA32_TSCDEADLINE:
+ data = kvm_get_lapic_tscdeadline_msr(vcpu);
+ break;
case MSR_IA32_MISC_ENABLE:
data = vcpu->arch.ia32_misc_enable_msr;
break;
*/
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:
r = !kvm_x86_ops->cpu_has_accelerated_tpr();
break;
case KVM_CAP_NR_VCPUS:
+ r = KVM_SOFT_MAX_VCPUS;
+ break;
+ case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
break;
case KVM_CAP_NR_MEMSLOTS:
r = 0;
break;
case KVM_CAP_IOMMU:
- r = iommu_found();
+ r = iommu_present(&pci_bus_type);
break;
case KVM_CAP_MCE:
r = KVM_MAX_MCE_BANKS;
case KVM_CAP_TSC_CONTROL:
r = kvm_has_tsc_control;
break;
+ case KVM_CAP_TSC_DEADLINE_TIMER:
+ r = boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER);
+ break;
default:
r = 0;
break;
}
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;
- kvm_get_msr(vcpu, MSR_IA32_TSC, &tsc);
- 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);
- kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc);
-}
-
-static int is_efer_nx(void)
-{
- unsigned long long efer = 0;
-
- rdmsrl_safe(MSR_EFER, &efer);
- return efer & EFER_NX;
-}
-
-static void cpuid_fix_nx_cap(struct kvm_vcpu *vcpu)
-{
- int i;
- struct kvm_cpuid_entry2 *e, *entry;
-
- entry = NULL;
- for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
- e = &vcpu->arch.cpuid_entries[i];
- if (e->function == 0x80000001) {
- entry = e;
- break;
- }
- }
- if (entry && (entry->edx & (1 << 20)) && !is_efer_nx()) {
- entry->edx &= ~(1 << 20);
- printk(KERN_INFO "kvm: guest NX capability removed\n");
- }
-}
-
-/* when an old userspace process fills a new kernel module */
-static int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
- struct kvm_cpuid *cpuid,
- struct kvm_cpuid_entry __user *entries)
-{
- int r, i;
- struct kvm_cpuid_entry *cpuid_entries;
-
- r = -E2BIG;
- if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
- goto out;
- r = -ENOMEM;
- cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry) * cpuid->nent);
- if (!cpuid_entries)
- goto out;
- r = -EFAULT;
- if (copy_from_user(cpuid_entries, entries,
- cpuid->nent * sizeof(struct kvm_cpuid_entry)))
- goto out_free;
- for (i = 0; i < cpuid->nent; i++) {
- vcpu->arch.cpuid_entries[i].function = cpuid_entries[i].function;
- vcpu->arch.cpuid_entries[i].eax = cpuid_entries[i].eax;
- vcpu->arch.cpuid_entries[i].ebx = cpuid_entries[i].ebx;
- vcpu->arch.cpuid_entries[i].ecx = cpuid_entries[i].ecx;
- vcpu->arch.cpuid_entries[i].edx = cpuid_entries[i].edx;
- vcpu->arch.cpuid_entries[i].index = 0;
- vcpu->arch.cpuid_entries[i].flags = 0;
- vcpu->arch.cpuid_entries[i].padding[0] = 0;
- vcpu->arch.cpuid_entries[i].padding[1] = 0;
- vcpu->arch.cpuid_entries[i].padding[2] = 0;
- }
- vcpu->arch.cpuid_nent = cpuid->nent;
- cpuid_fix_nx_cap(vcpu);
- r = 0;
- kvm_apic_set_version(vcpu);
- kvm_x86_ops->cpuid_update(vcpu);
- update_cpuid(vcpu);
-
-out_free:
- vfree(cpuid_entries);
-out:
- return r;
-}
-
-static int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
- struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries)
-{
- int r;
-
- r = -E2BIG;
- if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
- goto out;
- r = -EFAULT;
- if (copy_from_user(&vcpu->arch.cpuid_entries, entries,
- cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
- goto out;
- vcpu->arch.cpuid_nent = cpuid->nent;
- kvm_apic_set_version(vcpu);
- kvm_x86_ops->cpuid_update(vcpu);
- update_cpuid(vcpu);
- return 0;
-
-out:
- return r;
-}
-
-static int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
- struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries)
-{
- int r;
-
- r = -E2BIG;
- if (cpuid->nent < vcpu->arch.cpuid_nent)
- goto out;
- r = -EFAULT;
- if (copy_to_user(entries, &vcpu->arch.cpuid_entries,
- vcpu->arch.cpuid_nent * sizeof(struct kvm_cpuid_entry2)))
- goto out;
- return 0;
-
-out:
- cpuid->nent = vcpu->arch.cpuid_nent;
- return r;
-}
-
-static void cpuid_mask(u32 *word, int wordnum)
-{
- *word &= boot_cpu_data.x86_capability[wordnum];
-}
-
-static void do_cpuid_1_ent(struct kvm_cpuid_entry2 *entry, u32 function,
- u32 index)
-{
- entry->function = function;
- entry->index = index;
- cpuid_count(entry->function, entry->index,
- &entry->eax, &entry->ebx, &entry->ecx, &entry->edx);
- entry->flags = 0;
-}
-
-static bool supported_xcr0_bit(unsigned bit)
-{
- u64 mask = ((u64)1 << bit);
-
- return mask & (XSTATE_FP | XSTATE_SSE | XSTATE_YMM) & host_xcr0;
-}
-
-#define F(x) bit(X86_FEATURE_##x)
-
-static void do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
- u32 index, int *nent, int maxnent)
-{
- unsigned f_nx = is_efer_nx() ? F(NX) : 0;
-#ifdef CONFIG_X86_64
- unsigned f_gbpages = (kvm_x86_ops->get_lpage_level() == PT_PDPE_LEVEL)
- ? F(GBPAGES) : 0;
- unsigned f_lm = F(LM);
-#else
- unsigned f_gbpages = 0;
- unsigned f_lm = 0;
-#endif
- unsigned f_rdtscp = kvm_x86_ops->rdtscp_supported() ? F(RDTSCP) : 0;
-
- /* cpuid 1.edx */
- const u32 kvm_supported_word0_x86_features =
- F(FPU) | F(VME) | F(DE) | F(PSE) |
- F(TSC) | F(MSR) | F(PAE) | F(MCE) |
- F(CX8) | F(APIC) | 0 /* Reserved */ | F(SEP) |
- F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
- F(PAT) | F(PSE36) | 0 /* PSN */ | F(CLFLSH) |
- 0 /* Reserved, DS, ACPI */ | F(MMX) |
- F(FXSR) | F(XMM) | F(XMM2) | F(SELFSNOOP) |
- 0 /* HTT, TM, Reserved, PBE */;
- /* cpuid 0x80000001.edx */
- const u32 kvm_supported_word1_x86_features =
- F(FPU) | F(VME) | F(DE) | F(PSE) |
- F(TSC) | F(MSR) | F(PAE) | F(MCE) |
- F(CX8) | F(APIC) | 0 /* Reserved */ | F(SYSCALL) |
- F(MTRR) | F(PGE) | F(MCA) | F(CMOV) |
- F(PAT) | F(PSE36) | 0 /* Reserved */ |
- f_nx | 0 /* Reserved */ | F(MMXEXT) | F(MMX) |
- F(FXSR) | F(FXSR_OPT) | f_gbpages | f_rdtscp |
- 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
- /* cpuid 1.ecx */
- const u32 kvm_supported_word4_x86_features =
- F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64 */ | F(MWAIT) |
- 0 /* DS-CPL, VMX, SMX, EST */ |
- 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ |
- 0 /* Reserved */ | F(CX16) | 0 /* xTPR Update, PDCM */ |
- 0 /* Reserved, DCA */ | F(XMM4_1) |
- F(XMM4_2) | F(X2APIC) | F(MOVBE) | F(POPCNT) |
- 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
- F(F16C) | F(RDRAND);
- /* cpuid 0x80000001.ecx */
- const u32 kvm_supported_word6_x86_features =
- F(LAHF_LM) | F(CMP_LEGACY) | 0 /*SVM*/ | 0 /* ExtApicSpace */ |
- F(CR8_LEGACY) | F(ABM) | F(SSE4A) | F(MISALIGNSSE) |
- F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) |
- 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
-
- /* cpuid 0xC0000001.edx */
- const u32 kvm_supported_word5_x86_features =
- F(XSTORE) | F(XSTORE_EN) | F(XCRYPT) | F(XCRYPT_EN) |
- F(ACE2) | F(ACE2_EN) | F(PHE) | F(PHE_EN) |
- F(PMM) | F(PMM_EN);
-
- /* cpuid 7.0.ebx */
- const u32 kvm_supported_word9_x86_features =
- F(SMEP) | F(FSGSBASE) | F(ERMS);
-
- /* all calls to cpuid_count() should be made on the same cpu */
- get_cpu();
- do_cpuid_1_ent(entry, function, index);
- ++*nent;
-
- switch (function) {
- case 0:
- entry->eax = min(entry->eax, (u32)0xd);
- break;
- case 1:
- entry->edx &= kvm_supported_word0_x86_features;
- cpuid_mask(&entry->edx, 0);
- entry->ecx &= kvm_supported_word4_x86_features;
- cpuid_mask(&entry->ecx, 4);
- /* we support x2apic emulation even if host does not support
- * it since we emulate x2apic in software */
- entry->ecx |= F(X2APIC);
- break;
- /* function 2 entries are STATEFUL. That is, repeated cpuid commands
- * may return different values. This forces us to get_cpu() before
- * issuing the first command, and also to emulate this annoying behavior
- * in kvm_emulate_cpuid() using KVM_CPUID_FLAG_STATE_READ_NEXT */
- case 2: {
- int t, times = entry->eax & 0xff;
-
- entry->flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
- entry->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
- for (t = 1; t < times && *nent < maxnent; ++t) {
- do_cpuid_1_ent(&entry[t], function, 0);
- entry[t].flags |= KVM_CPUID_FLAG_STATEFUL_FUNC;
- ++*nent;
- }
- break;
- }
- /* function 4 has additional index. */
- case 4: {
- int i, cache_type;
-
- entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- /* read more entries until cache_type is zero */
- for (i = 1; *nent < maxnent; ++i) {
- cache_type = entry[i - 1].eax & 0x1f;
- if (!cache_type)
- break;
- do_cpuid_1_ent(&entry[i], function, i);
- entry[i].flags |=
- KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- ++*nent;
- }
- break;
- }
- case 7: {
- entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- /* Mask ebx against host capbability word 9 */
- if (index == 0) {
- entry->ebx &= kvm_supported_word9_x86_features;
- cpuid_mask(&entry->ebx, 9);
- } else
- entry->ebx = 0;
- entry->eax = 0;
- entry->ecx = 0;
- entry->edx = 0;
- break;
- }
- case 9:
- break;
- /* function 0xb has additional index. */
- case 0xb: {
- int i, level_type;
-
- entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- /* read more entries until level_type is zero */
- for (i = 1; *nent < maxnent; ++i) {
- level_type = entry[i - 1].ecx & 0xff00;
- if (!level_type)
- break;
- do_cpuid_1_ent(&entry[i], function, i);
- entry[i].flags |=
- KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- ++*nent;
- }
- break;
- }
- case 0xd: {
- int idx, i;
-
- entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- for (idx = 1, i = 1; *nent < maxnent && idx < 64; ++idx) {
- do_cpuid_1_ent(&entry[i], function, idx);
- if (entry[i].eax == 0 || !supported_xcr0_bit(idx))
- continue;
- entry[i].flags |=
- KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
- ++*nent;
- ++i;
- }
- break;
- }
- case KVM_CPUID_SIGNATURE: {
- char signature[12] = "KVMKVMKVM\0\0";
- u32 *sigptr = (u32 *)signature;
- entry->eax = 0;
- entry->ebx = sigptr[0];
- entry->ecx = sigptr[1];
- entry->edx = sigptr[2];
- break;
- }
- case KVM_CPUID_FEATURES:
- entry->eax = (1 << KVM_FEATURE_CLOCKSOURCE) |
- (1 << KVM_FEATURE_NOP_IO_DELAY) |
- (1 << KVM_FEATURE_CLOCKSOURCE2) |
- (1 << KVM_FEATURE_ASYNC_PF) |
- (1 << KVM_FEATURE_CLOCKSOURCE_STABLE_BIT);
-
- if (sched_info_on())
- entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
-
- entry->ebx = 0;
- entry->ecx = 0;
- entry->edx = 0;
- break;
- case 0x80000000:
- entry->eax = min(entry->eax, 0x8000001a);
- break;
- case 0x80000001:
- entry->edx &= kvm_supported_word1_x86_features;
- cpuid_mask(&entry->edx, 1);
- entry->ecx &= kvm_supported_word6_x86_features;
- cpuid_mask(&entry->ecx, 6);
- break;
- case 0x80000008: {
- unsigned g_phys_as = (entry->eax >> 16) & 0xff;
- unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U);
- unsigned phys_as = entry->eax & 0xff;
-
- if (!g_phys_as)
- g_phys_as = phys_as;
- entry->eax = g_phys_as | (virt_as << 8);
- entry->ebx = entry->edx = 0;
- break;
- }
- case 0x80000019:
- entry->ecx = entry->edx = 0;
- break;
- case 0x8000001a:
- break;
- case 0x8000001d:
- break;
- /*Add support for Centaur's CPUID instruction*/
- case 0xC0000000:
- /*Just support up to 0xC0000004 now*/
- entry->eax = min(entry->eax, 0xC0000004);
- break;
- case 0xC0000001:
- entry->edx &= kvm_supported_word5_x86_features;
- cpuid_mask(&entry->edx, 5);
- break;
- case 3: /* Processor serial number */
- case 5: /* MONITOR/MWAIT */
- case 6: /* Thermal management */
- case 0xA: /* Architectural Performance Monitoring */
- case 0x80000007: /* Advanced power management */
- case 0xC0000002:
- case 0xC0000003:
- case 0xC0000004:
- default:
- entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
- break;
- }
-
- kvm_x86_ops->set_supported_cpuid(function, entry);
-
- put_cpu();
-}
-
-#undef F
-
-static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
- struct kvm_cpuid_entry2 __user *entries)
-{
- struct kvm_cpuid_entry2 *cpuid_entries;
- int limit, nent = 0, r = -E2BIG;
- u32 func;
-
- if (cpuid->nent < 1)
- goto out;
- if (cpuid->nent > KVM_MAX_CPUID_ENTRIES)
- cpuid->nent = KVM_MAX_CPUID_ENTRIES;
- r = -ENOMEM;
- cpuid_entries = vmalloc(sizeof(struct kvm_cpuid_entry2) * cpuid->nent);
- if (!cpuid_entries)
- goto out;
-
- do_cpuid_ent(&cpuid_entries[0], 0, 0, &nent, cpuid->nent);
- limit = cpuid_entries[0].eax;
- for (func = 1; func <= limit && nent < cpuid->nent; ++func)
- do_cpuid_ent(&cpuid_entries[nent], func, 0,
- &nent, cpuid->nent);
- r = -E2BIG;
- if (nent >= cpuid->nent)
- goto out_free;
-
- do_cpuid_ent(&cpuid_entries[nent], 0x80000000, 0, &nent, cpuid->nent);
- limit = cpuid_entries[nent - 1].eax;
- for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
- do_cpuid_ent(&cpuid_entries[nent], func, 0,
- &nent, cpuid->nent);
-
-
-
- r = -E2BIG;
- if (nent >= cpuid->nent)
- goto out_free;
-
- /* Add support for Centaur's CPUID instruction. */
- if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR) {
- do_cpuid_ent(&cpuid_entries[nent], 0xC0000000, 0,
- &nent, cpuid->nent);
-
- r = -E2BIG;
- if (nent >= cpuid->nent)
- goto out_free;
-
- limit = cpuid_entries[nent - 1].eax;
- for (func = 0xC0000001;
- func <= limit && nent < cpuid->nent; ++func)
- do_cpuid_ent(&cpuid_entries[nent], func, 0,
- &nent, cpuid->nent);
-
- r = -E2BIG;
- if (nent >= cpuid->nent)
- goto out_free;
- }
-
- do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_SIGNATURE, 0, &nent,
- cpuid->nent);
-
- r = -E2BIG;
- if (nent >= cpuid->nent)
- goto out_free;
-
- do_cpuid_ent(&cpuid_entries[nent], KVM_CPUID_FEATURES, 0, &nent,
- cpuid->nent);
-
- r = -E2BIG;
- if (nent >= cpuid->nent)
- goto out_free;
-
- r = -EFAULT;
- if (copy_to_user(entries, cpuid_entries,
- nent * sizeof(struct kvm_cpuid_entry2)))
- goto out_free;
- cpuid->nent = nent;
- r = 0;
-
-out_free:
- vfree(cpuid_entries);
-out:
- return r;
+ vcpu->arch.last_host_tsc = native_read_tsc();
}
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
+ process_nmi(vcpu);
events->exception.injected =
vcpu->arch.exception.pending &&
!kvm_exception_is_soft(vcpu->arch.exception.nr);
KVM_X86_SHADOW_INT_MOV_SS | KVM_X86_SHADOW_INT_STI);
events->nmi.injected = vcpu->arch.nmi_injected;
- events->nmi.pending = vcpu->arch.nmi_pending;
+ events->nmi.pending = vcpu->arch.nmi_pending != 0;
events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);
events->nmi.pad = 0;
| KVM_VCPUEVENT_VALID_SHADOW))
return -EINVAL;
+ process_nmi(vcpu);
vcpu->arch.exception.pending = events->exception.injected;
vcpu->arch.exception.nr = events->exception.nr;
vcpu->arch.exception.has_error_code = events->exception.has_error_code;
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;
return 0;
}
+/**
+ * write_protect_slot - write protect a slot for dirty logging
+ * @kvm: the kvm instance
+ * @memslot: the slot we protect
+ * @dirty_bitmap: the bitmap indicating which pages are dirty
+ * @nr_dirty_pages: the number of dirty pages
+ *
+ * We have two ways to find all sptes to protect:
+ * 1. Use kvm_mmu_slot_remove_write_access() which walks all shadow pages and
+ * checks ones that have a spte mapping a page in the slot.
+ * 2. Use kvm_mmu_rmap_write_protect() for each gfn found in the bitmap.
+ *
+ * Generally speaking, if there are not so many dirty pages compared to the
+ * number of shadow pages, we should use the latter.
+ *
+ * Note that letting others write into a page marked dirty in the old bitmap
+ * by using the remaining tlb entry is not a problem. That page will become
+ * write protected again when we flush the tlb and then be reported dirty to
+ * the user space by copying the old bitmap.
+ */
+static void write_protect_slot(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
+ 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;
+
+ kvm_mmu_rmap_write_protect(kvm, gfn, memslot);
+ }
+ kvm_flush_remote_tlbs(kvm);
+ } else
+ kvm_mmu_slot_remove_write_access(kvm, memslot->id);
+
+ spin_unlock(&kvm->mmu_lock);
+}
+
/*
* Get (and clear) the dirty memory log for a memory slot.
*/
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
struct kvm_dirty_log *log)
{
- int r, i;
+ int r;
struct kvm_memory_slot *memslot;
- unsigned long n;
- unsigned long is_dirty = 0;
+ unsigned long n, nr_dirty_pages;
mutex_lock(&kvm->slots_lock);
if (log->slot >= KVM_MEMORY_SLOTS)
goto out;
- memslot = &kvm->memslots->memslots[log->slot];
+ memslot = id_to_memslot(kvm->memslots, log->slot);
r = -ENOENT;
if (!memslot->dirty_bitmap)
goto out;
n = kvm_dirty_bitmap_bytes(memslot);
-
- for (i = 0; !is_dirty && i < n/sizeof(long); i++)
- is_dirty = memslot->dirty_bitmap[i];
+ nr_dirty_pages = memslot->nr_dirty_pages;
/* If nothing is dirty, don't bother messing with page tables. */
- if (is_dirty) {
+ if (nr_dirty_pages) {
struct kvm_memslots *slots, *old_slots;
- unsigned long *dirty_bitmap;
+ unsigned long *dirty_bitmap, *dirty_bitmap_head;
- dirty_bitmap = memslot->dirty_bitmap_head;
- if (memslot->dirty_bitmap == dirty_bitmap)
- dirty_bitmap += n / sizeof(long);
- memset(dirty_bitmap, 0, n);
+ dirty_bitmap = memslot->dirty_bitmap;
+ dirty_bitmap_head = memslot->dirty_bitmap_head;
+ if (dirty_bitmap == dirty_bitmap_head)
+ dirty_bitmap_head += n / sizeof(long);
+ 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));
- slots->memslots[log->slot].dirty_bitmap = dirty_bitmap;
- slots->generation++;
+
+ memslot = id_to_memslot(slots, log->slot);
+ memslot->nr_dirty_pages = 0;
+ memslot->dirty_bitmap = dirty_bitmap_head;
+ update_memslots(slots, NULL);
old_slots = kvm->memslots;
rcu_assign_pointer(kvm->memslots, slots);
synchronize_srcu_expedited(&kvm->srcu);
- dirty_bitmap = old_slots->memslots[log->slot].dirty_bitmap;
kfree(old_slots);
- spin_lock(&kvm->mmu_lock);
- kvm_mmu_slot_remove_write_access(kvm, log->slot);
- spin_unlock(&kvm->mmu_lock);
+ write_protect_slot(kvm, memslot, dirty_bitmap, nr_dirty_pages);
r = -EFAULT;
if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n))
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) {
if (r) {
mutex_lock(&kvm->slots_lock);
kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
- &vpic->dev);
+ &vpic->dev_master);
+ kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
+ &vpic->dev_slave);
+ kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
+ &vpic->dev_eclr);
mutex_unlock(&kvm->slots_lock);
kfree(vpic);
goto create_irqchip_unlock;
}
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;
kvm_x86_ops->get_segment(vcpu, var, seg);
}
-static gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
-{
- return gpa;
-}
-
-static gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
+gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
{
gpa_t t_gpa;
struct x86_exception exception;
return 0;
}
-static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt,
- unsigned long addr,
- void *val,
- unsigned int bytes,
- struct x86_exception *exception)
+int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
+ const void *val, int bytes)
{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
- gpa_t gpa;
- int handled, ret;
+ int ret;
+
+ ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
+ if (ret < 0)
+ return 0;
+ kvm_mmu_pte_write(vcpu, gpa, val, bytes);
+ return 1;
+}
+
+struct read_write_emulator_ops {
+ int (*read_write_prepare)(struct kvm_vcpu *vcpu, void *val,
+ int bytes);
+ int (*read_write_emulate)(struct kvm_vcpu *vcpu, gpa_t gpa,
+ void *val, int bytes);
+ int (*read_write_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa,
+ int bytes, void *val);
+ int (*read_write_exit_mmio)(struct kvm_vcpu *vcpu, gpa_t gpa,
+ void *val, int bytes);
+ bool write;
+};
+static int read_prepare(struct kvm_vcpu *vcpu, void *val, int bytes)
+{
if (vcpu->mmio_read_completed) {
memcpy(val, vcpu->mmio_data, bytes);
trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
vcpu->mmio_phys_addr, *(u64 *)val);
vcpu->mmio_read_completed = 0;
- return X86EMUL_CONTINUE;
+ return 1;
}
- ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, false);
-
- if (ret < 0)
- return X86EMUL_PROPAGATE_FAULT;
-
- if (ret)
- goto mmio;
-
- if (kvm_read_guest_virt(ctxt, addr, val, bytes, exception)
- == X86EMUL_CONTINUE)
- return X86EMUL_CONTINUE;
-
-mmio:
- /*
- * Is this MMIO handled locally?
- */
- handled = vcpu_mmio_read(vcpu, gpa, bytes, val);
-
- if (handled == bytes)
- return X86EMUL_CONTINUE;
+ return 0;
+}
- gpa += handled;
- bytes -= handled;
- val += handled;
+static int read_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
+ void *val, int bytes)
+{
+ return !kvm_read_guest(vcpu->kvm, gpa, val, bytes);
+}
- trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0);
+static int write_emulate(struct kvm_vcpu *vcpu, gpa_t gpa,
+ void *val, int bytes)
+{
+ return emulator_write_phys(vcpu, gpa, val, bytes);
+}
- vcpu->mmio_needed = 1;
- vcpu->run->exit_reason = KVM_EXIT_MMIO;
- vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa;
- vcpu->mmio_size = bytes;
- vcpu->run->mmio.len = min(vcpu->mmio_size, 8);
- vcpu->run->mmio.is_write = vcpu->mmio_is_write = 0;
- vcpu->mmio_index = 0;
+static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val)
+{
+ trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val);
+ return vcpu_mmio_write(vcpu, gpa, bytes, val);
+}
+static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
+ void *val, int bytes)
+{
+ trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0);
return X86EMUL_IO_NEEDED;
}
-int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
- const void *val, int bytes)
+static int write_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
+ void *val, int bytes)
{
- int ret;
-
- ret = kvm_write_guest(vcpu->kvm, gpa, val, bytes);
- if (ret < 0)
- return 0;
- kvm_mmu_pte_write(vcpu, gpa, val, bytes, 1);
- return 1;
+ memcpy(vcpu->mmio_data, val, bytes);
+ memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8);
+ return X86EMUL_CONTINUE;
}
-static int emulator_write_emulated_onepage(unsigned long addr,
- const void *val,
- unsigned int bytes,
- struct x86_exception *exception,
- struct kvm_vcpu *vcpu)
+static struct read_write_emulator_ops read_emultor = {
+ .read_write_prepare = read_prepare,
+ .read_write_emulate = read_emulate,
+ .read_write_mmio = vcpu_mmio_read,
+ .read_write_exit_mmio = read_exit_mmio,
+};
+
+static struct read_write_emulator_ops write_emultor = {
+ .read_write_emulate = write_emulate,
+ .read_write_mmio = write_mmio,
+ .read_write_exit_mmio = write_exit_mmio,
+ .write = true,
+};
+
+static int emulator_read_write_onepage(unsigned long addr, void *val,
+ unsigned int bytes,
+ struct x86_exception *exception,
+ struct kvm_vcpu *vcpu,
+ struct read_write_emulator_ops *ops)
{
gpa_t gpa;
int handled, ret;
+ bool write = ops->write;
- ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, true);
+ if (ops->read_write_prepare &&
+ ops->read_write_prepare(vcpu, val, bytes))
+ return X86EMUL_CONTINUE;
+
+ ret = vcpu_mmio_gva_to_gpa(vcpu, addr, &gpa, exception, write);
if (ret < 0)
return X86EMUL_PROPAGATE_FAULT;
if (ret)
goto mmio;
- if (emulator_write_phys(vcpu, gpa, val, bytes))
+ if (ops->read_write_emulate(vcpu, gpa, val, bytes))
return X86EMUL_CONTINUE;
mmio:
- trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val);
/*
* Is this MMIO handled locally?
*/
- handled = vcpu_mmio_write(vcpu, gpa, bytes, val);
+ handled = ops->read_write_mmio(vcpu, gpa, bytes, val);
if (handled == bytes)
return X86EMUL_CONTINUE;
val += handled;
vcpu->mmio_needed = 1;
- memcpy(vcpu->mmio_data, val, bytes);
vcpu->run->exit_reason = KVM_EXIT_MMIO;
vcpu->run->mmio.phys_addr = vcpu->mmio_phys_addr = gpa;
vcpu->mmio_size = bytes;
vcpu->run->mmio.len = min(vcpu->mmio_size, 8);
- vcpu->run->mmio.is_write = vcpu->mmio_is_write = 1;
- memcpy(vcpu->run->mmio.data, vcpu->mmio_data, 8);
+ vcpu->run->mmio.is_write = vcpu->mmio_is_write = write;
vcpu->mmio_index = 0;
- return X86EMUL_CONTINUE;
+ return ops->read_write_exit_mmio(vcpu, gpa, val, bytes);
}
-int emulator_write_emulated(struct x86_emulate_ctxt *ctxt,
- unsigned long addr,
- const void *val,
- unsigned int bytes,
- struct x86_exception *exception)
+int emulator_read_write(struct x86_emulate_ctxt *ctxt, unsigned long addr,
+ void *val, unsigned int bytes,
+ struct x86_exception *exception,
+ struct read_write_emulator_ops *ops)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
int rc, now;
now = -addr & ~PAGE_MASK;
- rc = emulator_write_emulated_onepage(addr, val, now, exception,
- vcpu);
+ rc = emulator_read_write_onepage(addr, val, now, exception,
+ vcpu, ops);
+
if (rc != X86EMUL_CONTINUE)
return rc;
addr += now;
val += now;
bytes -= now;
}
- return emulator_write_emulated_onepage(addr, val, bytes, exception,
- vcpu);
+
+ return emulator_read_write_onepage(addr, val, bytes, exception,
+ vcpu, ops);
+}
+
+static int emulator_read_emulated(struct x86_emulate_ctxt *ctxt,
+ unsigned long addr,
+ void *val,
+ unsigned int bytes,
+ struct x86_exception *exception)
+{
+ return emulator_read_write(ctxt, addr, val, bytes,
+ exception, &read_emultor);
+}
+
+int emulator_write_emulated(struct x86_emulate_ctxt *ctxt,
+ unsigned long addr,
+ const void *val,
+ unsigned int bytes,
+ struct x86_exception *exception)
+{
+ return emulator_read_write(ctxt, addr, (void *)val, bytes,
+ exception, &write_emultor);
}
#define CMPXCHG_TYPE(t, ptr, old, new) \
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 X86EMUL_CMPXCHG_FAILED;
- kvm_mmu_pte_write(vcpu, gpa, new, bytes, 1);
+ kvm_mmu_pte_write(vcpu, gpa, new, bytes);
return X86EMUL_CONTINUE;
return r;
}
-
-static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
- int size, unsigned short port, void *val,
- unsigned int count)
+static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size,
+ unsigned short port, void *val,
+ unsigned int count, bool in)
{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
-
- if (vcpu->arch.pio.count)
- goto data_avail;
-
- trace_kvm_pio(0, port, size, count);
+ trace_kvm_pio(!in, port, size, count);
vcpu->arch.pio.port = port;
- vcpu->arch.pio.in = 1;
+ vcpu->arch.pio.in = in;
vcpu->arch.pio.count = count;
vcpu->arch.pio.size = size;
if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
- data_avail:
- memcpy(val, vcpu->arch.pio_data, size * count);
vcpu->arch.pio.count = 0;
return 1;
}
vcpu->run->exit_reason = KVM_EXIT_IO;
- vcpu->run->io.direction = KVM_EXIT_IO_IN;
+ vcpu->run->io.direction = in ? KVM_EXIT_IO_IN : KVM_EXIT_IO_OUT;
vcpu->run->io.size = size;
vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
vcpu->run->io.count = count;
return 0;
}
-static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
- int size, unsigned short port,
- const void *val, unsigned int count)
+static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
+ int size, unsigned short port, void *val,
+ unsigned int count)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+ int ret;
- trace_kvm_pio(1, port, size, count);
-
- vcpu->arch.pio.port = port;
- vcpu->arch.pio.in = 0;
- vcpu->arch.pio.count = count;
- vcpu->arch.pio.size = size;
-
- memcpy(vcpu->arch.pio_data, val, size * count);
+ if (vcpu->arch.pio.count)
+ goto data_avail;
- if (!kernel_pio(vcpu, vcpu->arch.pio_data)) {
+ ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
+ if (ret) {
+data_avail:
+ memcpy(val, vcpu->arch.pio_data, size * count);
vcpu->arch.pio.count = 0;
return 1;
}
- vcpu->run->exit_reason = KVM_EXIT_IO;
- vcpu->run->io.direction = KVM_EXIT_IO_OUT;
- vcpu->run->io.size = size;
- vcpu->run->io.data_offset = KVM_PIO_PAGE_OFFSET * PAGE_SIZE;
- vcpu->run->io.count = count;
- vcpu->run->io.port = port;
-
return 0;
}
+static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt,
+ int size, unsigned short port,
+ const void *val, unsigned int count)
+{
+ struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+
+ memcpy(vcpu->arch.pio_data, val, size * count);
+ return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false);
+}
+
static unsigned long get_segment_base(struct kvm_vcpu *vcpu, int seg)
{
return kvm_x86_ops->get_segment_base(vcpu, seg);
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)
kvm_set_rflags(vcpu, ctxt->eflags);
if (irq == NMI_VECTOR)
- vcpu->arch.nmi_pending = false;
+ vcpu->arch.nmi_pending = 0;
else
vcpu->arch.interrupt.pending = false;
return false;
}
+static bool retry_instruction(struct x86_emulate_ctxt *ctxt,
+ unsigned long cr2, int emulation_type)
+{
+ struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+ unsigned long last_retry_eip, last_retry_addr, gpa = cr2;
+
+ last_retry_eip = vcpu->arch.last_retry_eip;
+ last_retry_addr = vcpu->arch.last_retry_addr;
+
+ /*
+ * If the emulation is caused by #PF and it is non-page_table
+ * writing instruction, it means the VM-EXIT is caused by shadow
+ * page protected, we can zap the shadow page and retry this
+ * instruction directly.
+ *
+ * Note: if the guest uses a non-page-table modifying instruction
+ * on the PDE that points to the instruction, then we will unmap
+ * the instruction and go to an infinite loop. So, we cache the
+ * last retried eip and the last fault address, if we meet the eip
+ * and the address again, we can break out of the potential infinite
+ * loop.
+ */
+ vcpu->arch.last_retry_eip = vcpu->arch.last_retry_addr = 0;
+
+ if (!(emulation_type & EMULTYPE_RETRY))
+ return false;
+
+ if (x86_page_table_writing_insn(ctxt))
+ return false;
+
+ if (ctxt->eip == last_retry_eip && last_retry_addr == cr2)
+ return false;
+
+ vcpu->arch.last_retry_eip = ctxt->eip;
+ vcpu->arch.last_retry_addr = cr2;
+
+ if (!vcpu->arch.mmu.direct_map)
+ gpa = kvm_mmu_gva_to_gpa_write(vcpu, cr2, NULL);
+
+ kvm_mmu_unprotect_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+
+ return true;
+}
+
int x86_emulate_instruction(struct kvm_vcpu *vcpu,
unsigned long cr2,
int emulation_type,
trace_kvm_emulate_insn_start(vcpu);
++vcpu->stat.insn_emulation;
- if (r) {
+ if (r != EMULATION_OK) {
if (emulation_type & EMULTYPE_TRAP_UD)
return EMULATE_FAIL;
if (reexecute_instruction(vcpu, cr2))
return EMULATE_DONE;
}
+ if (retry_instruction(ctxt, cr2, emulation_type))
+ return EMULATE_DONE;
+
/* this is needed for vmware backdoor interface to work since it
changes registers values during IO operation */
if (vcpu->arch.emulate_regs_need_sync_from_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);
}
EXPORT_SYMBOL_GPL(kvm_emulate_halt);
-static inline gpa_t hc_gpa(struct kvm_vcpu *vcpu, unsigned long a0,
- unsigned long a1)
-{
- if (is_long_mode(vcpu))
- return a0;
- else
- return a0 | ((gpa_t)a1 << 32);
-}
-
int kvm_hv_hypercall(struct kvm_vcpu *vcpu)
{
u64 param, ingpa, outgpa, ret;
case KVM_HC_VAPIC_POLL_IRQ:
ret = 0;
break;
- case KVM_HC_MMU_OP:
- r = kvm_pv_mmu_op(vcpu, a0, hc_gpa(vcpu, a1, a2), &ret);
- break;
default:
ret = -KVM_ENOSYS;
break;
return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
}
-static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
-{
- struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
- int j, nent = vcpu->arch.cpuid_nent;
-
- e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
- /* when no next entry is found, the current entry[i] is reselected */
- for (j = i + 1; ; j = (j + 1) % nent) {
- struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
- if (ej->function == e->function) {
- ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
- return j;
- }
- }
- return 0; /* silence gcc, even though control never reaches here */
-}
-
-/* find an entry with matching function, matching index (if needed), and that
- * should be read next (if it's stateful) */
-static int is_matching_cpuid_entry(struct kvm_cpuid_entry2 *e,
- u32 function, u32 index)
-{
- if (e->function != function)
- return 0;
- if ((e->flags & KVM_CPUID_FLAG_SIGNIFCANT_INDEX) && e->index != index)
- return 0;
- if ((e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC) &&
- !(e->flags & KVM_CPUID_FLAG_STATE_READ_NEXT))
- return 0;
- return 1;
-}
-
-struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
- u32 function, u32 index)
-{
- int i;
- struct kvm_cpuid_entry2 *best = NULL;
-
- for (i = 0; i < vcpu->arch.cpuid_nent; ++i) {
- struct kvm_cpuid_entry2 *e;
-
- e = &vcpu->arch.cpuid_entries[i];
- if (is_matching_cpuid_entry(e, function, index)) {
- if (e->flags & KVM_CPUID_FLAG_STATEFUL_FUNC)
- move_to_next_stateful_cpuid_entry(vcpu, i);
- best = e;
- break;
- }
- }
- return best;
-}
-EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
-
-int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
-{
- struct kvm_cpuid_entry2 *best;
-
- best = kvm_find_cpuid_entry(vcpu, 0x80000000, 0);
- if (!best || best->eax < 0x80000008)
- goto not_found;
- best = kvm_find_cpuid_entry(vcpu, 0x80000008, 0);
- if (best)
- return best->eax & 0xff;
-not_found:
- return 36;
-}
-
-/*
- * If no match is found, check whether we exceed the vCPU's limit
- * and return the content of the highest valid _standard_ leaf instead.
- * This is to satisfy the CPUID specification.
- */
-static struct kvm_cpuid_entry2* check_cpuid_limit(struct kvm_vcpu *vcpu,
- u32 function, u32 index)
-{
- struct kvm_cpuid_entry2 *maxlevel;
-
- maxlevel = kvm_find_cpuid_entry(vcpu, function & 0x80000000, 0);
- if (!maxlevel || maxlevel->eax >= function)
- return NULL;
- if (function & 0x80000000) {
- maxlevel = kvm_find_cpuid_entry(vcpu, 0, 0);
- if (!maxlevel)
- return NULL;
- }
- return kvm_find_cpuid_entry(vcpu, maxlevel->eax, index);
-}
-
-void kvm_emulate_cpuid(struct kvm_vcpu *vcpu)
-{
- u32 function, index;
- struct kvm_cpuid_entry2 *best;
-
- function = kvm_register_read(vcpu, VCPU_REGS_RAX);
- index = kvm_register_read(vcpu, VCPU_REGS_RCX);
- kvm_register_write(vcpu, VCPU_REGS_RAX, 0);
- kvm_register_write(vcpu, VCPU_REGS_RBX, 0);
- kvm_register_write(vcpu, VCPU_REGS_RCX, 0);
- kvm_register_write(vcpu, VCPU_REGS_RDX, 0);
- best = kvm_find_cpuid_entry(vcpu, function, index);
-
- if (!best)
- best = check_cpuid_limit(vcpu, function, index);
-
- if (best) {
- kvm_register_write(vcpu, VCPU_REGS_RAX, best->eax);
- kvm_register_write(vcpu, VCPU_REGS_RBX, best->ebx);
- kvm_register_write(vcpu, VCPU_REGS_RCX, best->ecx);
- kvm_register_write(vcpu, VCPU_REGS_RDX, best->edx);
- }
- kvm_x86_ops->skip_emulated_instruction(vcpu);
- trace_kvm_cpuid(function,
- kvm_register_read(vcpu, VCPU_REGS_RAX),
- kvm_register_read(vcpu, VCPU_REGS_RBX),
- kvm_register_read(vcpu, VCPU_REGS_RCX),
- kvm_register_read(vcpu, VCPU_REGS_RDX));
-}
-EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
-
/*
* Check if userspace requested an interrupt window, and that the
* interrupt window is open.
/* try to inject new event if pending */
if (vcpu->arch.nmi_pending) {
if (kvm_x86_ops->nmi_allowed(vcpu)) {
- vcpu->arch.nmi_pending = false;
+ --vcpu->arch.nmi_pending;
vcpu->arch.nmi_injected = true;
kvm_x86_ops->set_nmi(vcpu);
}
}
}
+static void process_nmi(struct kvm_vcpu *vcpu)
+{
+ unsigned limit = 2;
+
+ /*
+ * x86 is limited to one NMI running, and one NMI pending after it.
+ * If an NMI is already in progress, limit further NMIs to just one.
+ * Otherwise, allow two (and we'll inject the first one immediately).
+ */
+ if (kvm_x86_ops->get_nmi_mask(vcpu) || vcpu->arch.nmi_injected)
+ limit = 1;
+
+ vcpu->arch.nmi_pending += atomic_xchg(&vcpu->arch.nmi_queued, 0);
+ vcpu->arch.nmi_pending = min(vcpu->arch.nmi_pending, limit);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+}
+
static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
{
int r;
- bool nmi_pending;
bool req_int_win = !irqchip_in_kernel(vcpu->kvm) &&
vcpu->run->request_interrupt_window;
+ bool req_immediate_exit = 0;
if (vcpu->requests) {
if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
}
if (kvm_check_request(KVM_REQ_STEAL_UPDATE, vcpu))
record_steal_time(vcpu);
-
+ if (kvm_check_request(KVM_REQ_NMI, vcpu))
+ 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);
if (unlikely(r))
goto out;
- /*
- * An NMI can be injected between local nmi_pending read and
- * vcpu->arch.nmi_pending read inside inject_pending_event().
- * But in that case, KVM_REQ_EVENT will be set, which makes
- * the race described above benign.
- */
- nmi_pending = ACCESS_ONCE(vcpu->arch.nmi_pending);
-
if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
inject_pending_event(vcpu);
/* enable NMI/IRQ window open exits if needed */
- if (nmi_pending)
+ if (vcpu->arch.nmi_pending)
kvm_x86_ops->enable_nmi_window(vcpu);
else if (kvm_cpu_has_interrupt(vcpu) || req_int_win)
kvm_x86_ops->enable_irq_window(vcpu);
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+ if (req_immediate_exit)
+ smp_send_reschedule(vcpu->cpu);
+
kvm_guest_enter();
if (unlikely(vcpu->arch.switch_db_regs)) {
if (hw_breakpoint_active())
hw_breakpoint_restore();
- kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc);
+ vcpu->arch.last_guest_tsc = kvm_x86_ops->read_l1_tsc(vcpu);
vcpu->mode = OUTSIDE_GUEST_MODE;
smp_wmb();
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);
if (r <= 0)
goto out;
- if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL)
- kvm_register_write(vcpu, VCPU_REGS_RAX,
- kvm_run->hypercall.ret);
-
r = __vcpu_run(vcpu);
out:
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)
mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
if (sregs->cr4 & X86_CR4_OSXSAVE)
- update_cpuid(vcpu);
+ kvm_update_cpuid(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
if (!is_long_mode(vcpu) && is_pae(vcpu)) {
int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
{
- vcpu->arch.nmi_pending = false;
+ atomic_set(&vcpu->arch.nmi_queued, 0);
+ vcpu->arch.nmi_pending = 0;
vcpu->arch.nmi_injected = false;
vcpu->arch.switch_db_regs = 0;
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;
kvm = vcpu->kvm;
vcpu->arch.emulate_ctxt.ops = &emulate_ops;
- vcpu->arch.walk_mmu = &vcpu->arch.mmu;
- vcpu->arch.mmu.root_hpa = INVALID_PAGE;
- vcpu->arch.mmu.translate_gpa = translate_gpa;
- vcpu->arch.nested_mmu.translate_gpa = translate_nested_gpa;
if (!irqchip_in_kernel(kvm) || kvm_vcpu_is_bsp(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
else
}
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: "
!vcpu->arch.apf.halted)
|| !list_empty_careful(&vcpu->async_pf.done)
|| vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
- || vcpu->arch.nmi_pending ||
+ || atomic_read(&vcpu->arch.nmi_queued) ||
(kvm_arch_interrupt_allowed(vcpu) &&
kvm_cpu_has_interrupt(vcpu));
}
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)
projects / linux-flexiantxendom0-3.2.10.git / blobdiff