* Copyright (C) 2006 Qumranet, Inc.
* Copyright (C) 2008 Qumranet, Inc.
* Copyright IBM Corporation, 2008
- * Copyright 2010 Red Hat, Inc. and/or its affilates.
+ * Copyright 2010 Red Hat, Inc. and/or its affiliates.
*
* Authors:
* Avi Kivity <avi@qumranet.com>
#include <asm/mce.h>
#include <asm/i387.h>
#include <asm/xcr.h>
+#include <asm/pvclock.h>
+#include <asm/div64.h>
#define MAX_IO_MSRS 256
#define CR0_RESERVED_BITS \
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
#define KVM_MAX_MCE_BANKS 32
-#define KVM_MCE_CAP_SUPPORTED MCG_CTL_P
+#define KVM_MCE_CAP_SUPPORTED (MCG_CTL_P | MCG_SER_P)
/* EFER defaults:
* - enable syscall per default because its emulated by KVM
u32 prev_nr;
int class1, class2;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
if (!vcpu->arch.exception.pending) {
queue:
vcpu->arch.exception.pending = true;
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception);
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
- u32 error_code)
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu)
{
+ unsigned error_code = vcpu->arch.fault.error_code;
+
++vcpu->stat.pf_guest;
- vcpu->arch.cr2 = addr;
+ vcpu->arch.cr2 = vcpu->arch.fault.address;
kvm_queue_exception_e(vcpu, PF_VECTOR, error_code);
}
+void kvm_propagate_fault(struct kvm_vcpu *vcpu)
+{
+ if (mmu_is_nested(vcpu) && !vcpu->arch.fault.nested)
+ vcpu->arch.nested_mmu.inject_page_fault(vcpu);
+ else
+ vcpu->arch.mmu.inject_page_fault(vcpu);
+
+ vcpu->arch.fault.nested = false;
+}
+
void kvm_inject_nmi(struct kvm_vcpu *vcpu)
{
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
vcpu->arch.nmi_pending = 1;
}
EXPORT_SYMBOL_GPL(kvm_inject_nmi);
}
EXPORT_SYMBOL_GPL(kvm_require_cpl);
+/*
+ * This function will be used to read from the physical memory of the currently
+ * running guest. The difference to kvm_read_guest_page is that this function
+ * can read from guest physical or from the guest's guest physical memory.
+ */
+int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+ gfn_t ngfn, void *data, int offset, int len,
+ u32 access)
+{
+ gfn_t real_gfn;
+ gpa_t ngpa;
+
+ ngpa = gfn_to_gpa(ngfn);
+ real_gfn = mmu->translate_gpa(vcpu, ngpa, access);
+ if (real_gfn == UNMAPPED_GVA)
+ return -EFAULT;
+
+ real_gfn = gpa_to_gfn(real_gfn);
+
+ return kvm_read_guest_page(vcpu->kvm, real_gfn, data, offset, len);
+}
+EXPORT_SYMBOL_GPL(kvm_read_guest_page_mmu);
+
+int kvm_read_nested_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn,
+ void *data, int offset, int len, u32 access)
+{
+ return kvm_read_guest_page_mmu(vcpu, vcpu->arch.walk_mmu, gfn,
+ data, offset, len, access);
+}
+
/*
* Load the pae pdptrs. Return true is they are all valid.
*/
-int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
+int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
{
gfn_t pdpt_gfn = cr3 >> PAGE_SHIFT;
unsigned offset = ((cr3 & (PAGE_SIZE-1)) >> 5) << 2;
int i;
int ret;
- u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];
+ u64 pdpte[ARRAY_SIZE(mmu->pdptrs)];
- ret = kvm_read_guest_page(vcpu->kvm, pdpt_gfn, pdpte,
- offset * sizeof(u64), sizeof(pdpte));
+ ret = kvm_read_guest_page_mmu(vcpu, mmu, pdpt_gfn, pdpte,
+ offset * sizeof(u64), sizeof(pdpte),
+ PFERR_USER_MASK|PFERR_WRITE_MASK);
if (ret < 0) {
ret = 0;
goto out;
}
ret = 1;
- memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs));
+ memcpy(mmu->pdptrs, pdpte, sizeof(mmu->pdptrs));
__set_bit(VCPU_EXREG_PDPTR,
(unsigned long *)&vcpu->arch.regs_avail);
__set_bit(VCPU_EXREG_PDPTR,
static bool pdptrs_changed(struct kvm_vcpu *vcpu)
{
- u64 pdpte[ARRAY_SIZE(vcpu->arch.pdptrs)];
+ u64 pdpte[ARRAY_SIZE(vcpu->arch.walk_mmu->pdptrs)];
bool changed = true;
+ int offset;
+ gfn_t gfn;
int r;
if (is_long_mode(vcpu) || !is_pae(vcpu))
(unsigned long *)&vcpu->arch.regs_avail))
return true;
- r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte));
+ gfn = (vcpu->arch.cr3 & ~31u) >> PAGE_SHIFT;
+ offset = (vcpu->arch.cr3 & ~31u) & (PAGE_SIZE - 1);
+ r = kvm_read_nested_guest_page(vcpu, gfn, pdpte, offset, sizeof(pdpte),
+ PFERR_USER_MASK | PFERR_WRITE_MASK);
if (r < 0)
goto out;
- changed = memcmp(pdpte, vcpu->arch.pdptrs, sizeof(pdpte)) != 0;
+ changed = memcmp(pdpte, vcpu->arch.walk_mmu->pdptrs, sizeof(pdpte)) != 0;
out:
return changed;
return 1;
} else
#endif
- if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.cr3))
+ if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
+ vcpu->arch.cr3))
return 1;
}
return 1;
} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
&& ((cr4 ^ old_cr4) & pdptr_bits)
- && !load_pdptrs(vcpu, vcpu->arch.cr3))
+ && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))
return 1;
if (cr4 & X86_CR4_VMXE)
if (is_pae(vcpu)) {
if (cr3 & CR3_PAE_RESERVED_BITS)
return 1;
- if (is_paging(vcpu) && !load_pdptrs(vcpu, cr3))
+ if (is_paging(vcpu) &&
+ !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
return 1;
}
/*
#ifdef CONFIG_X86_64
MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
- MSR_IA32_TSC, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
+ MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
};
static unsigned num_msrs_to_save;
/*
* The guest calculates current wall clock time by adding
- * system time (updated by kvm_write_guest_time below) to the
+ * system time (updated by kvm_guest_time_update below) to the
* wall clock specified here. guest system time equals host
* system time for us, thus we must fill in host boot time here.
*/
return quotient;
}
-static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
+static void kvm_get_time_scale(uint32_t scaled_khz, uint32_t base_khz,
+ s8 *pshift, u32 *pmultiplier)
{
- uint64_t nsecs = 1000000000LL;
+ uint64_t scaled64;
int32_t shift = 0;
uint64_t tps64;
uint32_t tps32;
- tps64 = tsc_khz * 1000LL;
- while (tps64 > nsecs*2) {
+ tps64 = base_khz * 1000LL;
+ scaled64 = scaled_khz * 1000LL;
+ while (tps64 > scaled64*2 || tps64 & 0xffffffff00000000ULL) {
tps64 >>= 1;
shift--;
}
tps32 = (uint32_t)tps64;
- while (tps32 <= (uint32_t)nsecs) {
- tps32 <<= 1;
+ while (tps32 <= scaled64 || scaled64 & 0xffffffff00000000ULL) {
+ if (scaled64 & 0xffffffff00000000ULL || tps32 & 0x80000000)
+ scaled64 >>= 1;
+ else
+ tps32 <<= 1;
shift++;
}
- hv_clock->tsc_shift = shift;
- hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);
+ *pshift = shift;
+ *pmultiplier = div_frac(scaled64, tps32);
- pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n",
- __func__, tsc_khz, hv_clock->tsc_shift,
- hv_clock->tsc_to_system_mul);
+ pr_debug("%s: base_khz %u => %u, shift %d, mul %u\n",
+ __func__, base_khz, scaled_khz, shift, *pmultiplier);
+}
+
+static inline u64 get_kernel_ns(void)
+{
+ struct timespec ts;
+
+ WARN_ON(preemptible());
+ ktime_get_ts(&ts);
+ monotonic_to_bootbased(&ts);
+ return timespec_to_ns(&ts);
}
static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
+unsigned long max_tsc_khz;
static inline int kvm_tsc_changes_freq(void)
{
return ret;
}
+static inline u64 nsec_to_cycles(u64 nsec)
+{
+ u64 ret;
+
+ WARN_ON(preemptible());
+ if (kvm_tsc_changes_freq())
+ printk_once(KERN_WARNING
+ "kvm: unreliable cycle conversion on adjustable rate TSC\n");
+ ret = nsec * __get_cpu_var(cpu_tsc_khz);
+ do_div(ret, USEC_PER_SEC);
+ return ret;
+}
+
+static void kvm_arch_set_tsc_khz(struct kvm *kvm, u32 this_tsc_khz)
+{
+ /* Compute a scale to convert nanoseconds in TSC cycles */
+ kvm_get_time_scale(this_tsc_khz, NSEC_PER_SEC / 1000,
+ &kvm->arch.virtual_tsc_shift,
+ &kvm->arch.virtual_tsc_mult);
+ kvm->arch.virtual_tsc_khz = this_tsc_khz;
+}
+
+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->kvm->arch.virtual_tsc_mult,
+ vcpu->kvm->arch.virtual_tsc_shift);
+ tsc += vcpu->arch.last_tsc_write;
+ return tsc;
+}
+
void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data)
{
struct kvm *kvm = vcpu->kvm;
u64 offset, ns, elapsed;
unsigned long flags;
- struct timespec ts;
+ s64 sdiff;
spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = data - native_read_tsc();
- ktime_get_ts(&ts);
- monotonic_to_bootbased(&ts);
- ns = timespec_to_ns(&ts);
+ ns = get_kernel_ns();
elapsed = ns - kvm->arch.last_tsc_nsec;
+ sdiff = data - kvm->arch.last_tsc_write;
+ if (sdiff < 0)
+ sdiff = -sdiff;
/*
- * Special case: identical write to TSC within 5 seconds of
+ * Special case: close write to TSC within 5 seconds of
* another CPU is interpreted as an attempt to synchronize
- * (the 5 seconds is to accomodate host load / swapping).
+ * The 5 seconds is to accomodate 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 kernel_ns value.
+ * or make a best guest using elapsed value.
*/
- if (data == kvm->arch.last_tsc_write && elapsed < 5ULL * NSEC_PER_SEC) {
+ if (sdiff < nsec_to_cycles(5ULL * NSEC_PER_SEC) &&
+ elapsed < 5ULL * NSEC_PER_SEC) {
if (!check_tsc_unstable()) {
offset = kvm->arch.last_tsc_offset;
pr_debug("kvm: matched tsc offset for %llu\n", data);
} else {
- u64 tsc_delta = elapsed * __get_cpu_var(cpu_tsc_khz);
- tsc_delta = tsc_delta / USEC_PER_SEC;
- offset += tsc_delta;
- pr_debug("kvm: adjusted tsc offset by %llu\n", tsc_delta);
+ u64 delta = nsec_to_cycles(elapsed);
+ offset += delta;
+ pr_debug("kvm: adjusted tsc offset by %llu\n", delta);
}
ns = kvm->arch.last_tsc_nsec;
}
/* 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;
}
EXPORT_SYMBOL_GPL(kvm_write_tsc);
-static int kvm_write_guest_time(struct kvm_vcpu *v)
+static int kvm_guest_time_update(struct kvm_vcpu *v)
{
- struct timespec ts;
unsigned long flags;
struct kvm_vcpu_arch *vcpu = &v->arch;
void *shared_kaddr;
unsigned long this_tsc_khz;
-
- if ((!vcpu->time_page))
- return 0;
+ s64 kernel_ns, max_kernel_ns;
+ u64 tsc_timestamp;
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
- kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp);
- ktime_get_ts(&ts);
- monotonic_to_bootbased(&ts);
+ kvm_get_msr(v, MSR_IA32_TSC, &tsc_timestamp);
+ kernel_ns = get_kernel_ns();
this_tsc_khz = __get_cpu_var(cpu_tsc_khz);
- local_irq_restore(flags);
if (unlikely(this_tsc_khz == 0)) {
- kvm_make_request(KVM_REQ_KVMCLOCK_UPDATE, v);
+ local_irq_restore(flags);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
return 1;
}
+ /*
+ * We may have to catch up the TSC to match elapsed wall clock
+ * time for two reasons, even if kvmclock is used.
+ * 1) CPU could have been running below the maximum TSC rate
+ * 2) Broken TSC compensation resets the base at each VCPU
+ * entry to avoid unknown leaps of TSC even when running
+ * again on the same CPU. This may cause apparent elapsed
+ * time to disappear, and the guest to stand still or run
+ * very slowly.
+ */
+ 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);
+ tsc_timestamp = tsc;
+ }
+ }
+
+ local_irq_restore(flags);
+
+ if (!vcpu->time_page)
+ return 0;
+
+ /*
+ * Time as measured by the TSC may go backwards when resetting the base
+ * tsc_timestamp. The reason for this is that the TSC resolution is
+ * higher than the resolution of the other clock scales. Thus, many
+ * possible measurments of the TSC correspond to one measurement of any
+ * other clock, and so a spread of values is possible. This is not a
+ * problem for the computation of the nanosecond clock; with TSC rates
+ * around 1GHZ, there can only be a few cycles which correspond to one
+ * nanosecond value, and any path through this code will inevitably
+ * take longer than that. However, with the kernel_ns value itself,
+ * the precision may be much lower, down to HZ granularity. If the
+ * first sampling of TSC against kernel_ns ends in the low part of the
+ * range, and the second in the high end of the range, we can get:
+ *
+ * (TSC - offset_low) * S + kns_old > (TSC - offset_high) * S + kns_new
+ *
+ * As the sampling errors potentially range in the thousands of cycles,
+ * it is possible such a time value has already been observed by the
+ * guest. To protect against this, we must compute the system time as
+ * 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) {
+ max_kernel_ns = vcpu->last_guest_tsc -
+ vcpu->hv_clock.tsc_timestamp;
+ max_kernel_ns = pvclock_scale_delta(max_kernel_ns,
+ vcpu->hv_clock.tsc_to_system_mul,
+ vcpu->hv_clock.tsc_shift);
+ max_kernel_ns += vcpu->last_kernel_ns;
+ }
+
if (unlikely(vcpu->hw_tsc_khz != this_tsc_khz)) {
- kvm_set_time_scale(this_tsc_khz, &vcpu->hv_clock);
+ kvm_get_time_scale(NSEC_PER_SEC / 1000, this_tsc_khz,
+ &vcpu->hv_clock.tsc_shift,
+ &vcpu->hv_clock.tsc_to_system_mul);
vcpu->hw_tsc_khz = this_tsc_khz;
}
- /* With all the info we got, fill in the values */
- vcpu->hv_clock.system_time = ts.tv_nsec +
- (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset;
+ if (max_kernel_ns > kernel_ns)
+ kernel_ns = max_kernel_ns;
+ /* With all the info we got, fill in the values */
+ vcpu->hv_clock.tsc_timestamp = tsc_timestamp;
+ vcpu->hv_clock.system_time = kernel_ns + v->kvm->arch.kvmclock_offset;
+ vcpu->last_kernel_ns = kernel_ns;
+ vcpu->last_guest_tsc = tsc_timestamp;
vcpu->hv_clock.flags = 0;
/*
return 0;
}
-static int kvm_request_guest_time_update(struct kvm_vcpu *v)
-{
- struct kvm_vcpu_arch *vcpu = &v->arch;
-
- if (!vcpu->time_page)
- return 0;
- kvm_make_request(KVM_REQ_KVMCLOCK_UPDATE, v);
- return 1;
-}
-
static bool msr_mtrr_valid(unsigned msr)
{
switch (msr) {
}
vcpu->arch.time = data;
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
/* we verify if the enable bit is set... */
if (!(data & 1))
kvm_release_page_clean(vcpu->arch.time_page);
vcpu->arch.time_page = NULL;
}
-
- kvm_request_guest_time_update(vcpu);
break;
}
case MSR_IA32_MCG_CTL:
pr_unimpl(vcpu, "unimplemented 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.
+ * Writes are only relevant for old K7 processors,
+ * all pre-dating SVM, but a recommended workaround from
+ * AMD for these chips. It is possible to speicify the
+ * affected processor models on the command line, hence
+ * the need to ignore the workaround.
+ */
+ break;
case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
if (kvm_hv_msr_partition_wide(msr)) {
int r;
case 0xcd: /* fsb frequency */
data = 3;
break;
+ /*
+ * MSR_EBC_FREQUENCY_ID
+ * Conservative value valid for even the basic CPU models.
+ * Models 0,1: 000 in bits 23:21 indicating a bus speed of
+ * 100MHz, model 2 000 in bits 18:16 indicating 100MHz,
+ * and 266MHz for model 3, or 4. Set Core Clock
+ * Frequency to System Bus Frequency Ratio to 1 (bits
+ * 31:24) even though these are only valid for CPU
+ * models > 2, however guests may end up dividing or
+ * multiplying by zero otherwise.
+ */
+ case MSR_EBC_FREQUENCY_ID:
+ data = 1 << 24;
+ break;
case MSR_IA32_APICBASE:
data = kvm_get_apic_base(vcpu);
break;
case MSR_IA32_MCG_STATUS:
case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
return get_msr_mce(vcpu, msr, pdata);
+ case MSR_K7_CLK_CTL:
+ /*
+ * Provide expected ramp-up count for K7. All other
+ * are set to zero, indicating minimum divisors for
+ * every field.
+ *
+ * This prevents guest kernels on AMD host with CPU
+ * type 6, model 8 and higher from exploding due to
+ * the rdmsr failing.
+ */
+ data = 0x20000000;
+ break;
case HV_X64_MSR_GUEST_OS_ID ... HV_X64_MSR_SINT15:
if (kvm_hv_msr_partition_wide(msr)) {
int r;
}
kvm_x86_ops->vcpu_load(vcpu, cpu);
- if (unlikely(vcpu->cpu != cpu)) {
+ if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
/* Make sure TSC doesn't go backwards */
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())
+ if (check_tsc_unstable()) {
kvm_x86_ops->adjust_tsc_offset(vcpu, -tsc_delta);
- kvm_migrate_timers(vcpu);
+ vcpu->arch.tsc_catchup = 1;
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
+ }
+ if (vcpu->cpu != cpu)
+ kvm_migrate_timers(vcpu);
vcpu->cpu = cpu;
}
}
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, AES */ | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX);
+ 0 /* Reserved*/ | F(AES) | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX) |
+ F(F16C);
/* cpuid 0x80000001.ecx */
const u32 kvm_supported_word6_x86_features =
- F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ |
+ 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(SSE5) |
- 0 /* SKINIT */ | 0 /* WDT */;
+ F(3DNOWPREFETCH) | 0 /* OSVW */ | 0 /* IBS */ | F(XOP) |
+ 0 /* SKINIT, WDT, LWP */ | F(FMA4) | F(TBM);
/* all calls to cpuid_count() should be made on the same cpu */
get_cpu();
return -ENXIO;
kvm_queue_interrupt(vcpu, irq->irq, false);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
return 0;
}
if (events->flags & KVM_VCPUEVENT_VALID_SIPI_VECTOR)
vcpu->arch.sipi_vector = events->sipi_vector;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
return 0;
}
r = 0;
switch (chip->chip_id) {
case KVM_IRQCHIP_PIC_MASTER:
- raw_spin_lock(&pic_irqchip(kvm)->lock);
+ spin_lock(&pic_irqchip(kvm)->lock);
memcpy(&pic_irqchip(kvm)->pics[0],
&chip->chip.pic,
sizeof(struct kvm_pic_state));
- raw_spin_unlock(&pic_irqchip(kvm)->lock);
+ spin_unlock(&pic_irqchip(kvm)->lock);
break;
case KVM_IRQCHIP_PIC_SLAVE:
- raw_spin_lock(&pic_irqchip(kvm)->lock);
+ spin_lock(&pic_irqchip(kvm)->lock);
memcpy(&pic_irqchip(kvm)->pics[1],
&chip->chip.pic,
sizeof(struct kvm_pic_state));
- raw_spin_unlock(&pic_irqchip(kvm)->lock);
+ spin_unlock(&pic_irqchip(kvm)->lock);
break;
case KVM_IRQCHIP_IOAPIC:
r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
break;
}
case KVM_SET_CLOCK: {
- struct timespec now;
struct kvm_clock_data user_ns;
u64 now_ns;
s64 delta;
goto out;
r = 0;
- ktime_get_ts(&now);
- now_ns = timespec_to_ns(&now);
+ local_irq_disable();
+ now_ns = get_kernel_ns();
delta = user_ns.clock - now_ns;
+ local_irq_enable();
kvm->arch.kvmclock_offset = delta;
break;
}
case KVM_GET_CLOCK: {
- struct timespec now;
struct kvm_clock_data user_ns;
u64 now_ns;
- ktime_get_ts(&now);
- now_ns = timespec_to_ns(&now);
+ local_irq_disable();
+ now_ns = get_kernel_ns();
user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
+ local_irq_enable();
user_ns.flags = 0;
r = -EFAULT;
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 t_gpa;
+ u32 error;
+
+ BUG_ON(!mmu_is_nested(vcpu));
+
+ /* NPT walks are always user-walks */
+ access |= PFERR_USER_MASK;
+ t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &error);
+ if (t_gpa == UNMAPPED_GVA)
+ vcpu->arch.fault.nested = true;
+
+ return t_gpa;
+}
+
gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
- return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, access, error);
+ return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
}
gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
access |= PFERR_FETCH_MASK;
- return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, access, error);
+ return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
}
gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
access |= PFERR_WRITE_MASK;
- return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, access, error);
+ return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
}
/* uses this to access any guest's mapped memory without checking CPL */
gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
{
- return vcpu->arch.mmu.gva_to_gpa(vcpu, gva, 0, error);
+ return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, error);
}
static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
int r = X86EMUL_CONTINUE;
while (bytes) {
- gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr, access, error);
+ gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access,
+ error);
unsigned offset = addr & (PAGE_SIZE-1);
unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset);
int ret;
int r = X86EMUL_CONTINUE;
while (bytes) {
- gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, addr,
- PFERR_WRITE_MASK, error);
+ gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr,
+ PFERR_WRITE_MASK,
+ error);
unsigned offset = addr & (PAGE_SIZE-1);
unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
int ret;
if (vcpu->arch.pio.count)
goto data_avail;
- trace_kvm_pio(1, port, size, 1);
+ trace_kvm_pio(0, port, size, 1);
vcpu->arch.pio.port = port;
vcpu->arch.pio.in = 1;
const void *val, unsigned int count,
struct kvm_vcpu *vcpu)
{
- trace_kvm_pio(0, port, size, 1);
+ trace_kvm_pio(1, port, size, 1);
vcpu->arch.pio.port = port;
vcpu->arch.pio.in = 0;
{
struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
if (ctxt->exception == PF_VECTOR)
- kvm_inject_page_fault(vcpu, ctxt->cr2, ctxt->error_code);
+ kvm_propagate_fault(vcpu);
else if (ctxt->error_code_valid)
kvm_queue_exception_e(vcpu, ctxt->exception, ctxt->error_code);
else
memcpy(c->regs, vcpu->arch.regs, sizeof c->regs);
}
+int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq)
+{
+ struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode;
+ int ret;
+
+ init_emulate_ctxt(vcpu);
+
+ vcpu->arch.emulate_ctxt.decode.op_bytes = 2;
+ vcpu->arch.emulate_ctxt.decode.ad_bytes = 2;
+ vcpu->arch.emulate_ctxt.decode.eip = vcpu->arch.emulate_ctxt.eip;
+ ret = emulate_int_real(&vcpu->arch.emulate_ctxt, &emulate_ops, irq);
+
+ if (ret != X86EMUL_CONTINUE)
+ return EMULATE_FAIL;
+
+ vcpu->arch.emulate_ctxt.eip = c->eip;
+ memcpy(vcpu->arch.regs, c->regs, sizeof c->regs);
+ kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip);
+ kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+
+ if (irq == NMI_VECTOR)
+ vcpu->arch.nmi_pending = false;
+ else
+ vcpu->arch.interrupt.pending = false;
+
+ return EMULATE_DONE;
+}
+EXPORT_SYMBOL_GPL(kvm_inject_realmode_interrupt);
+
static int handle_emulation_failure(struct kvm_vcpu *vcpu)
{
++vcpu->stat.insn_emulation_fail;
vcpu->arch.emulate_ctxt.perm_ok = false;
r = x86_decode_insn(&vcpu->arch.emulate_ctxt);
+ if (r == X86EMUL_PROPAGATE_FAULT)
+ goto done;
+
trace_kvm_emulate_insn_start(vcpu);
/* Only allow emulation of specific instructions on #UD
restart:
r = x86_emulate_insn(&vcpu->arch.emulate_ctxt);
- if (r) { /* emulation failed */
+ if (r == EMULATION_FAILED) {
if (reexecute_instruction(vcpu, cr2))
return EMULATE_DONE;
return handle_emulation_failure(vcpu);
}
- r = EMULATE_DONE;
-
- if (vcpu->arch.emulate_ctxt.exception >= 0)
+done:
+ if (vcpu->arch.emulate_ctxt.exception >= 0) {
inject_emulated_exception(vcpu);
- else if (vcpu->arch.pio.count) {
+ r = EMULATE_DONE;
+ } else if (vcpu->arch.pio.count) {
if (!vcpu->arch.pio.in)
vcpu->arch.pio.count = 0;
r = EMULATE_DO_MMIO;
if (vcpu->mmio_is_write)
vcpu->mmio_needed = 0;
r = EMULATE_DO_MMIO;
- } else if (vcpu->arch.emulate_ctxt.restart)
+ } else if (r == EMULATION_RESTART)
goto restart;
+ else
+ r = EMULATE_DONE;
toggle_interruptibility(vcpu, vcpu->arch.emulate_ctxt.interruptibility);
kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
memcpy(vcpu->arch.regs, c->regs, sizeof c->regs);
kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip);
kvm_for_each_vcpu(i, vcpu, kvm) {
if (vcpu->cpu != freq->cpu)
continue;
- if (!kvm_request_guest_time_update(vcpu))
- continue;
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
if (vcpu->cpu != smp_processor_id())
send_ipi = 1;
}
{
int cpu;
+ max_tsc_khz = tsc_khz;
register_hotcpu_notifier(&kvmclock_cpu_notifier_block);
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+#ifdef CONFIG_CPU_FREQ
+ struct cpufreq_policy policy;
+ memset(&policy, 0, sizeof(policy));
+ cpufreq_get_policy(&policy, get_cpu());
+ if (policy.cpuinfo.max_freq)
+ max_tsc_khz = policy.cpuinfo.max_freq;
+#endif
cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
CPUFREQ_TRANSITION_NOTIFIER);
}
+ pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
for_each_online_cpu(cpu)
smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
}
kvm_mmu_unload(vcpu);
if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
__kvm_migrate_timers(vcpu);
- if (kvm_check_request(KVM_REQ_KVMCLOCK_UPDATE, vcpu)) {
- r = kvm_write_guest_time(vcpu);
+ if (kvm_check_request(KVM_REQ_CLOCK_UPDATE, vcpu)) {
+ r = kvm_guest_time_update(vcpu);
if (unlikely(r))
goto out;
}
if (unlikely(r))
goto out;
+ if (kvm_check_request(KVM_REQ_EVENT, vcpu) || req_int_win) {
+ inject_pending_event(vcpu);
+
+ /* enable NMI/IRQ window open exits if needed */
+ 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);
+
+ if (kvm_lapic_enabled(vcpu)) {
+ update_cr8_intercept(vcpu);
+ kvm_lapic_sync_to_vapic(vcpu);
+ }
+ }
+
preempt_disable();
kvm_x86_ops->prepare_guest_switch(vcpu);
smp_wmb();
local_irq_enable();
preempt_enable();
+ kvm_x86_ops->cancel_injection(vcpu);
r = 1;
goto out;
}
- inject_pending_event(vcpu);
-
- /* enable NMI/IRQ window open exits if needed */
- 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);
-
- if (kvm_lapic_enabled(vcpu)) {
- update_cr8_intercept(vcpu);
- kvm_lapic_sync_to_vapic(vcpu);
- }
-
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
kvm_guest_enter();
if (hw_breakpoint_active())
hw_breakpoint_restore();
+ kvm_get_msr(vcpu, MSR_IA32_TSC, &vcpu->arch.last_guest_tsc);
+
atomic_set(&vcpu->guest_mode, 0);
smp_wmb();
local_irq_enable();
if (!irqchip_in_kernel(vcpu->kvm))
kvm_set_cr8(vcpu, kvm_run->cr8);
- if (vcpu->arch.pio.count || vcpu->mmio_needed ||
- vcpu->arch.emulate_ctxt.restart) {
+ if (vcpu->arch.pio.count || vcpu->mmio_needed) {
if (vcpu->mmio_needed) {
memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
vcpu->mmio_read_completed = 1;
vcpu->arch.exception.pending = false;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
return 0;
}
struct kvm_mp_state *mp_state)
{
vcpu->arch.mp_state = mp_state->mp_state;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
return 0;
}
memcpy(vcpu->arch.regs, c->regs, sizeof c->regs);
kvm_rip_write(vcpu, vcpu->arch.emulate_ctxt.eip);
kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
return EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvm_task_switch);
mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
if (!is_long_mode(vcpu) && is_pae(vcpu)) {
- load_pdptrs(vcpu, vcpu->arch.cr3);
+ load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3);
mmu_reset_needed = 1;
}
!is_protmode(vcpu))
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
return 0;
}
vcpu->arch.dr6 = DR6_FIXED_1;
vcpu->arch.dr7 = DR7_FIXED_1;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+
return kvm_x86_ops->vcpu_reset(vcpu);
}
int kvm_arch_hardware_enable(void *garbage)
{
+ struct kvm *kvm;
+ struct kvm_vcpu *vcpu;
+ int i;
+
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);
}
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);
+ if (!kvm->arch.virtual_tsc_khz)
+ kvm_arch_set_tsc_khz(kvm, max_tsc_khz);
+
r = kvm_mmu_create(vcpu);
if (r < 0)
goto fail_free_pio_data;
kvm_is_linear_rip(vcpu, vcpu->arch.singlestep_rip))
rflags |= X86_EFLAGS_TF;
kvm_x86_ops->set_rflags(vcpu, rflags);
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
}
EXPORT_SYMBOL_GPL(kvm_set_rflags);
git.openpandora.org / pandora-kernel.git / blobdiff