* 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 <linux/slab.h>
#include <linux/perf_event.h>
#include <linux/uaccess.h>
+#include <linux/hash.h>
#include <trace/events/kvm.h>
#define CREATE_TRACE_POINTS
#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
u64 __read_mostly host_xcr0;
-static inline u32 bit(int bitno)
+static inline void kvm_async_pf_hash_reset(struct kvm_vcpu *vcpu)
{
- return 1 << (bitno & 31);
+ int i;
+ for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU); i++)
+ vcpu->arch.apf.gfns[i] = ~0;
}
static void kvm_on_user_return(struct user_return_notifier *urn)
}
EXPORT_SYMBOL_GPL(kvm_requeue_exception);
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu)
+void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err)
{
- unsigned error_code = vcpu->arch.fault.error_code;
+ if (err)
+ kvm_inject_gp(vcpu, 0);
+ else
+ kvm_x86_ops->skip_emulated_instruction(vcpu);
+}
+EXPORT_SYMBOL_GPL(kvm_complete_insn_gp);
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
+{
++vcpu->stat.pf_guest;
- vcpu->arch.cr2 = vcpu->arch.fault.address;
- kvm_queue_exception_e(vcpu, PF_VECTOR, error_code);
+ vcpu->arch.cr2 = fault->address;
+ kvm_queue_exception_e(vcpu, PF_VECTOR, fault->error_code);
}
-void kvm_propagate_fault(struct kvm_vcpu *vcpu)
+void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault)
{
- if (mmu_is_nested(vcpu) && !vcpu->arch.fault.nested)
- vcpu->arch.nested_mmu.inject_page_fault(vcpu);
+ if (mmu_is_nested(vcpu) && !fault->nested_page_fault)
+ vcpu->arch.nested_mmu.inject_page_fault(vcpu, fault);
else
- vcpu->arch.mmu.inject_page_fault(vcpu);
-
- vcpu->arch.fault.nested = false;
+ vcpu->arch.mmu.inject_page_fault(vcpu, fault);
}
void kvm_inject_nmi(struct kvm_vcpu *vcpu)
(unsigned long *)&vcpu->arch.regs_avail))
return true;
- gfn = (vcpu->arch.cr3 & ~31u) >> PAGE_SHIFT;
- offset = (vcpu->arch.cr3 & ~31u) & (PAGE_SIZE - 1);
+ gfn = (kvm_read_cr3(vcpu) & ~31u) >> PAGE_SHIFT;
+ offset = (kvm_read_cr3(vcpu) & ~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)
} else
#endif
if (is_pae(vcpu) && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
- vcpu->arch.cr3))
+ kvm_read_cr3(vcpu)))
return 1;
}
kvm_x86_ops->set_cr0(vcpu, cr0);
+ if ((cr0 ^ old_cr0) & X86_CR0_PG)
+ kvm_clear_async_pf_completion_queue(vcpu);
+
if ((cr0 ^ old_cr0) & update_bits)
kvm_mmu_reset_context(vcpu);
return 0;
return 1;
} else if (is_paging(vcpu) && (cr4 & X86_CR4_PAE)
&& ((cr4 ^ old_cr4) & pdptr_bits)
- && !load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3))
+ && !load_pdptrs(vcpu, vcpu->arch.walk_mmu,
+ kvm_read_cr3(vcpu)))
return 1;
if (cr4 & X86_CR4_VMXE)
int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
- if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) {
+ if (cr3 == kvm_read_cr3(vcpu) && !pdptrs_changed(vcpu)) {
kvm_mmu_sync_roots(vcpu);
kvm_mmu_flush_tlb(vcpu);
return 0;
if (unlikely(!gfn_to_memslot(vcpu->kvm, cr3 >> PAGE_SHIFT)))
return 1;
vcpu->arch.cr3 = cr3;
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
vcpu->arch.mmu.new_cr3(vcpu);
return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr3);
-int __kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
+int kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
{
if (cr8 & CR8_RESERVED_BITS)
return 1;
vcpu->arch.cr8 = cr8;
return 0;
}
-
-void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
-{
- if (__kvm_set_cr8(vcpu, cr8))
- kvm_inject_gp(vcpu, 0);
-}
EXPORT_SYMBOL_GPL(kvm_set_cr8);
unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu)
* kvm-specific. Those are put in the beginning of the list.
*/
-#define KVM_SAVE_MSRS_BEGIN 7
+#define KVM_SAVE_MSRS_BEGIN 8
static u32 msrs_to_save[] = {
MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
MSR_KVM_SYSTEM_TIME_NEW, MSR_KVM_WALL_CLOCK_NEW,
HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
- HV_X64_MSR_APIC_ASSIST_PAGE,
+ HV_X64_MSR_APIC_ASSIST_PAGE, MSR_KVM_ASYNC_PF_EN,
MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
MSR_STAR,
#ifdef CONFIG_X86_64
kvm_x86_ops->set_efer(vcpu, efer);
vcpu->arch.mmu.base_role.nxe = (efer & EFER_NX) && !tdp_enabled;
- kvm_mmu_reset_context(vcpu);
/* Update reserved bits */
if ((efer ^ old_efer) & EFER_NX)
/*
* 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)
}
static DEFINE_PER_CPU(unsigned long, cpu_tsc_khz);
+unsigned long max_tsc_khz;
static inline int kvm_tsc_changes_freq(void)
{
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);
+ ret = nsec * __this_cpu_read(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;
/* 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)
{
unsigned long flags;
struct kvm_vcpu_arch *vcpu = &v->arch;
s64 kernel_ns, max_kernel_ns;
u64 tsc_timestamp;
- if ((!vcpu->time_page))
- return 0;
-
/* Keep irq disabled to prevent changes to the clock */
local_irq_save(flags);
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);
+ this_tsc_khz = __this_cpu_read(cpu_tsc_khz);
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
}
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;
}
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) {
return 0;
}
+static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
+{
+ gpa_t gpa = data & ~0x3f;
+
+ /* Bits 2:5 are resrved, Should be zero */
+ if (data & 0x3c)
+ return 1;
+
+ vcpu->arch.apf.msr_val = data;
+
+ if (!(data & KVM_ASYNC_PF_ENABLED)) {
+ kvm_clear_async_pf_completion_queue(vcpu);
+ kvm_async_pf_hash_reset(vcpu);
+ return 0;
+ }
+
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+ return 1;
+
+ vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
+ kvm_async_pf_wakeup_all(vcpu);
+ return 0;
+}
+
int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
{
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_KVM_ASYNC_PF_EN:
+ if (kvm_pv_enable_async_pf(vcpu, data))
+ return 1;
+ break;
case MSR_IA32_MCG_CTL:
case MSR_IA32_MCG_STATUS:
case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
case MSR_KVM_SYSTEM_TIME_NEW:
data = vcpu->arch.time;
break;
+ case MSR_KVM_ASYNC_PF_EN:
+ data = vcpu->arch.apf.msr_val;
+ break;
case MSR_IA32_P5_MC_ADDR:
case MSR_IA32_P5_MC_TYPE:
case MSR_IA32_MCG_CAP:
case KVM_CAP_NOP_IO_DELAY:
case KVM_CAP_MP_STATE:
case KVM_CAP_SYNC_MMU:
+ case KVM_CAP_USER_NMI:
case KVM_CAP_REINJECT_CONTROL:
case KVM_CAP_IRQ_INJECT_STATUS:
case KVM_CAP_ASSIGN_DEV_IRQ:
case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
case KVM_CAP_XSAVE:
+ case KVM_CAP_ASYNC_PF:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
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;
}
}
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)
{
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) | 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();
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;
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;
}
!kvm_exception_is_soft(vcpu->arch.exception.nr);
events->exception.nr = vcpu->arch.exception.nr;
events->exception.has_error_code = vcpu->arch.exception.has_error_code;
+ events->exception.pad = 0;
events->exception.error_code = vcpu->arch.exception.error_code;
events->interrupt.injected =
events->nmi.injected = vcpu->arch.nmi_injected;
events->nmi.pending = vcpu->arch.nmi_pending;
events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);
+ events->nmi.pad = 0;
events->sipi_vector = vcpu->arch.sipi_vector;
events->flags = (KVM_VCPUEVENT_VALID_NMI_PENDING
| KVM_VCPUEVENT_VALID_SIPI_VECTOR
| KVM_VCPUEVENT_VALID_SHADOW);
+ memset(&events->reserved, 0, sizeof(events->reserved));
}
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
dbgregs->dr6 = vcpu->arch.dr6;
dbgregs->dr7 = vcpu->arch.dr7;
dbgregs->flags = 0;
+ memset(&dbgregs->reserved, 0, sizeof(dbgregs->reserved));
}
static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
sizeof(ps->channels));
ps->flags = kvm->arch.vpit->pit_state.flags;
mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ memset(&ps->reserved, 0, sizeof(ps->reserved));
return r;
}
struct kvm_memslots *slots, *old_slots;
unsigned long *dirty_bitmap;
- spin_lock(&kvm->mmu_lock);
- kvm_mmu_slot_remove_write_access(kvm, log->slot);
- spin_unlock(&kvm->mmu_lock);
-
- r = -ENOMEM;
- dirty_bitmap = vmalloc(n);
- if (!dirty_bitmap)
- goto out;
+ dirty_bitmap = memslot->dirty_bitmap_head;
+ if (memslot->dirty_bitmap == dirty_bitmap)
+ dirty_bitmap += n / sizeof(long);
memset(dirty_bitmap, 0, n);
r = -ENOMEM;
slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
- if (!slots) {
- vfree(dirty_bitmap);
+ if (!slots)
goto out;
- }
memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots));
slots->memslots[log->slot].dirty_bitmap = dirty_bitmap;
+ slots->generation++;
old_slots = kvm->memslots;
rcu_assign_pointer(kvm->memslots, slots);
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);
+
r = -EFAULT;
- if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n)) {
- vfree(dirty_bitmap);
+ if (copy_to_user(log->dirty_bitmap, dirty_bitmap, n))
goto out;
- }
- vfree(dirty_bitmap);
} else {
r = -EFAULT;
if (clear_user(log->dirty_bitmap, n))
if (vpic) {
r = kvm_ioapic_init(kvm);
if (r) {
+ mutex_lock(&kvm->slots_lock);
kvm_io_bus_unregister_dev(kvm, KVM_PIO_BUS,
&vpic->dev);
+ mutex_unlock(&kvm->slots_lock);
kfree(vpic);
goto create_irqchip_unlock;
}
smp_wmb();
r = kvm_setup_default_irq_routing(kvm);
if (r) {
+ mutex_lock(&kvm->slots_lock);
mutex_lock(&kvm->irq_lock);
kvm_ioapic_destroy(kvm);
kvm_destroy_pic(kvm);
mutex_unlock(&kvm->irq_lock);
+ mutex_unlock(&kvm->slots_lock);
}
create_irqchip_unlock:
mutex_unlock(&kvm->lock);
goto out;
r = 0;
+ local_irq_disable();
now_ns = get_kernel_ns();
delta = user_ns.clock - now_ns;
+ local_irq_enable();
kvm->arch.kvmclock_offset = delta;
break;
}
struct kvm_clock_data user_ns;
u64 now_ns;
+ local_irq_disable();
now_ns = get_kernel_ns();
user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
+ local_irq_enable();
user_ns.flags = 0;
+ memset(&user_ns.pad, 0, sizeof(user_ns.pad));
r = -EFAULT;
if (copy_to_user(argp, &user_ns, sizeof(user_ns)))
static gpa_t translate_nested_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
{
gpa_t t_gpa;
- u32 error;
+ struct x86_exception exception;
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;
+ t_gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, gpa, access, &exception);
return t_gpa;
}
-gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva,
+ struct x86_exception *exception)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
- return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
+ return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception);
}
- gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+ gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva,
+ struct x86_exception *exception)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
access |= PFERR_FETCH_MASK;
- return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
+ return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception);
}
-gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error)
+gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva,
+ struct x86_exception *exception)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
access |= PFERR_WRITE_MASK;
- return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, error);
+ return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, access, exception);
}
/* 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)
+gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
+ struct x86_exception *exception)
{
- return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, error);
+ return vcpu->arch.walk_mmu->gva_to_gpa(vcpu, gva, 0, exception);
}
static int kvm_read_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
struct kvm_vcpu *vcpu, u32 access,
- u32 *error)
+ struct x86_exception *exception)
{
void *data = val;
int r = X86EMUL_CONTINUE;
while (bytes) {
gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr, access,
- error);
+ exception);
unsigned offset = addr & (PAGE_SIZE-1);
unsigned toread = min(bytes, (unsigned)PAGE_SIZE - offset);
int ret;
- if (gpa == UNMAPPED_GVA) {
- r = X86EMUL_PROPAGATE_FAULT;
- goto out;
- }
+ if (gpa == UNMAPPED_GVA)
+ return X86EMUL_PROPAGATE_FAULT;
ret = kvm_read_guest(vcpu->kvm, gpa, data, toread);
if (ret < 0) {
r = X86EMUL_IO_NEEDED;
/* used for instruction fetching */
static int kvm_fetch_guest_virt(gva_t addr, void *val, unsigned int bytes,
- struct kvm_vcpu *vcpu, u32 *error)
+ struct kvm_vcpu *vcpu,
+ struct x86_exception *exception)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
return kvm_read_guest_virt_helper(addr, val, bytes, vcpu,
- access | PFERR_FETCH_MASK, error);
+ access | PFERR_FETCH_MASK,
+ exception);
}
static int kvm_read_guest_virt(gva_t addr, void *val, unsigned int bytes,
- struct kvm_vcpu *vcpu, u32 *error)
+ struct kvm_vcpu *vcpu,
+ struct x86_exception *exception)
{
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
- error);
+ exception);
}
static int kvm_read_guest_virt_system(gva_t addr, void *val, unsigned int bytes,
- struct kvm_vcpu *vcpu, u32 *error)
+ struct kvm_vcpu *vcpu,
+ struct x86_exception *exception)
{
- return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, error);
+ return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception);
}
static int kvm_write_guest_virt_system(gva_t addr, void *val,
unsigned int bytes,
struct kvm_vcpu *vcpu,
- u32 *error)
+ struct x86_exception *exception)
{
void *data = val;
int r = X86EMUL_CONTINUE;
while (bytes) {
gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr,
PFERR_WRITE_MASK,
- error);
+ exception);
unsigned offset = addr & (PAGE_SIZE-1);
unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
int ret;
- if (gpa == UNMAPPED_GVA) {
- r = X86EMUL_PROPAGATE_FAULT;
- goto out;
- }
+ if (gpa == UNMAPPED_GVA)
+ return X86EMUL_PROPAGATE_FAULT;
ret = kvm_write_guest(vcpu->kvm, gpa, data, towrite);
if (ret < 0) {
r = X86EMUL_IO_NEEDED;
static int emulator_read_emulated(unsigned long addr,
void *val,
unsigned int bytes,
- unsigned int *error_code,
+ struct x86_exception *exception,
struct kvm_vcpu *vcpu)
{
gpa_t gpa;
return X86EMUL_CONTINUE;
}
- gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, error_code);
+ gpa = kvm_mmu_gva_to_gpa_read(vcpu, addr, exception);
if (gpa == UNMAPPED_GVA)
return X86EMUL_PROPAGATE_FAULT;
if ((gpa & PAGE_MASK) == APIC_DEFAULT_PHYS_BASE)
goto mmio;
- if (kvm_read_guest_virt(addr, val, bytes, vcpu, NULL)
- == X86EMUL_CONTINUE)
+ if (kvm_read_guest_virt(addr, val, bytes, vcpu, exception)
+ == X86EMUL_CONTINUE)
return X86EMUL_CONTINUE;
mmio:
}
int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
- const void *val, int bytes)
+ const void *val, int bytes)
{
int ret;
static int emulator_write_emulated_onepage(unsigned long addr,
const void *val,
unsigned int bytes,
- unsigned int *error_code,
+ struct x86_exception *exception,
struct kvm_vcpu *vcpu)
{
gpa_t gpa;
- gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, error_code);
+ gpa = kvm_mmu_gva_to_gpa_write(vcpu, addr, exception);
if (gpa == UNMAPPED_GVA)
return X86EMUL_PROPAGATE_FAULT;
int emulator_write_emulated(unsigned long addr,
const void *val,
unsigned int bytes,
- unsigned int *error_code,
+ struct x86_exception *exception,
struct kvm_vcpu *vcpu)
{
/* Crossing a page boundary? */
int rc, now;
now = -addr & ~PAGE_MASK;
- rc = emulator_write_emulated_onepage(addr, val, now, error_code,
+ rc = emulator_write_emulated_onepage(addr, val, now, exception,
vcpu);
if (rc != X86EMUL_CONTINUE)
return rc;
val += now;
bytes -= now;
}
- return emulator_write_emulated_onepage(addr, val, bytes, error_code,
+ return emulator_write_emulated_onepage(addr, val, bytes, exception,
vcpu);
}
const void *old,
const void *new,
unsigned int bytes,
- unsigned int *error_code,
+ struct x86_exception *exception,
struct kvm_vcpu *vcpu)
{
gpa_t gpa;
emul_write:
printk_once(KERN_WARNING "kvm: emulating exchange as write\n");
- return emulator_write_emulated(addr, new, bytes, error_code, vcpu);
+ return emulator_write_emulated(addr, new, bytes, exception, vcpu);
}
static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
if (vcpu->arch.pio.count)
goto data_avail;
- trace_kvm_pio(0, port, size, 1);
+ trace_kvm_pio(0, port, size, count);
vcpu->arch.pio.port = port;
vcpu->arch.pio.in = 1;
const void *val, unsigned int count,
struct kvm_vcpu *vcpu)
{
- trace_kvm_pio(1, port, size, 1);
+ trace_kvm_pio(1, port, size, count);
vcpu->arch.pio.port = port;
vcpu->arch.pio.in = 0;
return X86EMUL_CONTINUE;
if (kvm_x86_ops->has_wbinvd_exit()) {
+ int cpu = get_cpu();
+
+ cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
wbinvd_ipi, NULL, 1);
+ put_cpu();
cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
- }
- wbinvd();
+ } else
+ wbinvd();
return X86EMUL_CONTINUE;
}
EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd);
value = vcpu->arch.cr2;
break;
case 3:
- value = vcpu->arch.cr3;
+ value = kvm_read_cr3(vcpu);
break;
case 4:
value = kvm_read_cr4(vcpu);
res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
break;
case 8:
- res = __kvm_set_cr8(vcpu, val & 0xfUL);
+ res = kvm_set_cr8(vcpu, val);
break;
default:
vcpu_printf(vcpu, "%s: unexpected cr %u\n", __func__, cr);
static void inject_emulated_exception(struct kvm_vcpu *vcpu)
{
struct x86_emulate_ctxt *ctxt = &vcpu->arch.emulate_ctxt;
- if (ctxt->exception == PF_VECTOR)
- kvm_propagate_fault(vcpu);
- else if (ctxt->error_code_valid)
- kvm_queue_exception_e(vcpu, ctxt->exception, ctxt->error_code);
+ if (ctxt->exception.vector == PF_VECTOR)
+ kvm_propagate_fault(vcpu, &ctxt->exception);
+ else if (ctxt->exception.error_code_valid)
+ kvm_queue_exception_e(vcpu, ctxt->exception.vector,
+ ctxt->exception.error_code);
else
- kvm_queue_exception(vcpu, ctxt->exception);
+ kvm_queue_exception(vcpu, ctxt->exception.vector);
}
static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
memcpy(c->regs, vcpu->arch.regs, sizeof c->regs);
}
-int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq)
+int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip)
{
struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode;
int ret;
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;
+ vcpu->arch.emulate_ctxt.decode.eip = vcpu->arch.emulate_ctxt.eip +
+ inc_eip;
ret = emulate_int_real(&vcpu->arch.emulate_ctxt, &emulate_ops, irq);
if (ret != X86EMUL_CONTINUE)
static int handle_emulation_failure(struct kvm_vcpu *vcpu)
{
+ int r = EMULATE_DONE;
+
++vcpu->stat.insn_emulation_fail;
trace_kvm_emulate_insn_failed(vcpu);
- vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
- vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
- vcpu->run->internal.ndata = 0;
+ if (!is_guest_mode(vcpu)) {
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->internal.ndata = 0;
+ r = EMULATE_FAIL;
+ }
kvm_queue_exception(vcpu, UD_VECTOR);
- return EMULATE_FAIL;
+
+ return r;
}
static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
return false;
}
-int emulate_instruction(struct kvm_vcpu *vcpu,
- unsigned long cr2,
- u16 error_code,
- int emulation_type)
+int x86_emulate_instruction(struct kvm_vcpu *vcpu,
+ unsigned long cr2,
+ int emulation_type,
+ void *insn,
+ int insn_len)
{
int r;
struct decode_cache *c = &vcpu->arch.emulate_ctxt.decode;
if (!(emulation_type & EMULTYPE_NO_DECODE)) {
init_emulate_ctxt(vcpu);
vcpu->arch.emulate_ctxt.interruptibility = 0;
- vcpu->arch.emulate_ctxt.exception = -1;
+ vcpu->arch.emulate_ctxt.have_exception = false;
vcpu->arch.emulate_ctxt.perm_ok = false;
- r = x86_decode_insn(&vcpu->arch.emulate_ctxt);
+ r = x86_decode_insn(&vcpu->arch.emulate_ctxt, insn, insn_len);
if (r == X86EMUL_PROPAGATE_FAULT)
goto done;
}
done:
- if (vcpu->arch.emulate_ctxt.exception >= 0) {
+ if (vcpu->arch.emulate_ctxt.have_exception) {
inject_emulated_exception(vcpu);
r = EMULATE_DONE;
} else if (vcpu->arch.pio.count) {
return r;
}
-EXPORT_SYMBOL_GPL(emulate_instruction);
+EXPORT_SYMBOL_GPL(x86_emulate_instruction);
int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
{
static void tsc_bad(void *info)
{
- __get_cpu_var(cpu_tsc_khz) = 0;
+ __this_cpu_write(cpu_tsc_khz, 0);
}
static void tsc_khz_changed(void *data)
khz = cpufreq_quick_get(raw_smp_processor_id());
if (!khz)
khz = tsc_khz;
- __get_cpu_var(cpu_tsc_khz) = khz;
+ __this_cpu_write(cpu_tsc_khz, khz);
}
static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
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));
+ cpu = get_cpu();
+ cpufreq_get_policy(&policy, cpu);
+ if (policy.cpuinfo.max_freq)
+ max_tsc_khz = policy.cpuinfo.max_freq;
+ put_cpu();
+#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_x86_ops = ops;
kvm_mmu_set_nonpresent_ptes(0ull, 0ull);
- kvm_mmu_set_base_ptes(PT_PRESENT_MASK);
kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
PT_DIRTY_MASK, PT64_NX_MASK, 0);
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;
}
vcpu->fpu_active = 0;
kvm_x86_ops->fpu_deactivate(vcpu);
}
+ if (kvm_check_request(KVM_REQ_APF_HALT, vcpu)) {
+ /* Page is swapped out. Do synthetic halt */
+ vcpu->arch.apf.halted = true;
+ r = 1;
+ goto out;
+ }
}
r = kvm_mmu_reload(vcpu);
r = 1;
while (r > 0) {
- if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
+ if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
+ !vcpu->arch.apf.halted)
r = vcpu_enter_guest(vcpu);
else {
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
vcpu->arch.mp_state =
KVM_MP_STATE_RUNNABLE;
case KVM_MP_STATE_RUNNABLE:
+ vcpu->arch.apf.halted = false;
break;
case KVM_MP_STATE_SIPI_RECEIVED:
default:
vcpu->run->exit_reason = KVM_EXIT_INTR;
++vcpu->stat.request_irq_exits;
}
+
+ kvm_check_async_pf_completion(vcpu);
+
if (signal_pending(current)) {
r = -EINTR;
vcpu->run->exit_reason = KVM_EXIT_INTR;
int r;
sigset_t sigsaved;
+ if (!tsk_used_math(current) && init_fpu(current))
+ return -ENOMEM;
+
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
}
/* re-sync apic's tpr */
- if (!irqchip_in_kernel(vcpu->kvm))
- kvm_set_cr8(vcpu, kvm_run->cr8);
+ if (!irqchip_in_kernel(vcpu->kvm)) {
+ if (kvm_set_cr8(vcpu, kvm_run->cr8) != 0) {
+ r = -EINVAL;
+ goto out;
+ }
+ }
if (vcpu->arch.pio.count || vcpu->mmio_needed) {
if (vcpu->mmio_needed) {
vcpu->mmio_needed = 0;
}
vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
- r = emulate_instruction(vcpu, 0, 0, EMULTYPE_NO_DECODE);
+ r = emulate_instruction(vcpu, EMULTYPE_NO_DECODE);
srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
if (r != EMULATE_DONE) {
r = 0;
sregs->cr0 = kvm_read_cr0(vcpu);
sregs->cr2 = vcpu->arch.cr2;
- sregs->cr3 = vcpu->arch.cr3;
+ sregs->cr3 = kvm_read_cr3(vcpu);
sregs->cr4 = kvm_read_cr4(vcpu);
sregs->cr8 = kvm_get_cr8(vcpu);
sregs->efer = vcpu->arch.efer;
kvm_x86_ops->set_gdt(vcpu, &dt);
vcpu->arch.cr2 = sregs->cr2;
- mmu_reset_needed |= vcpu->arch.cr3 != sregs->cr3;
+ mmu_reset_needed |= kvm_read_cr3(vcpu) != sregs->cr3;
vcpu->arch.cr3 = sregs->cr3;
+ __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
kvm_set_cr8(vcpu, sregs->cr8);
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);
if (!is_long_mode(vcpu) && is_pae(vcpu)) {
- load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3);
+ load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
mmu_reset_needed = 1;
}
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
+ vcpu->arch.apf.msr_val = 0;
+
vcpu_load(vcpu);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
vcpu->arch.dr7 = DR7_FIXED_1;
kvm_make_request(KVM_REQ_EVENT, vcpu);
+ vcpu->arch.apf.msr_val = 0;
+
+ kvm_clear_async_pf_completion_queue(vcpu);
+ kvm_async_pf_hash_reset(vcpu);
+ vcpu->arch.apf.halted = false;
return kvm_x86_ops->vcpu_reset(vcpu);
}
list_for_each_entry(kvm, &vm_list, vm_list)
kvm_for_each_vcpu(i, vcpu, kvm)
if (vcpu->cpu == smp_processor_id())
- kvm_request_guest_time_update(vcpu);
+ kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
return kvm_x86_ops->hardware_enable(garbage);
}
}
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;
if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL))
goto fail_free_mce_banks;
+ kvm_async_pf_hash_reset(vcpu);
+
return 0;
fail_free_mce_banks:
kfree(vcpu->arch.mce_banks);
free_page((unsigned long)vcpu->arch.pio_data);
}
-struct kvm *kvm_arch_create_vm(void)
+int kvm_arch_init_vm(struct kvm *kvm)
{
- struct kvm *kvm = kzalloc(sizeof(struct kvm), GFP_KERNEL);
-
- if (!kvm)
- return ERR_PTR(-ENOMEM);
-
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
spin_lock_init(&kvm->arch.tsc_write_lock);
- return kvm;
+ return 0;
}
static void kvm_unload_vcpu_mmu(struct kvm_vcpu *vcpu)
/*
* Unpin any mmu pages first.
*/
- kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ kvm_clear_async_pf_completion_queue(vcpu);
kvm_unload_vcpu_mmu(vcpu);
+ }
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_arch_vcpu_free(vcpu);
kfree(kvm->arch.vpic);
kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
- kvm_free_physmem(kvm);
if (kvm->arch.apic_access_page)
put_page(kvm->arch.apic_access_page);
if (kvm->arch.ept_identity_pagetable)
put_page(kvm->arch.ept_identity_pagetable);
- cleanup_srcu_struct(&kvm->srcu);
- kfree(kvm);
}
int kvm_arch_prepare_memory_region(struct kvm *kvm,
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
- return vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE
+ return (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE &&
+ !vcpu->arch.apf.halted)
+ || !list_empty_careful(&vcpu->async_pf.done)
|| vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED
|| vcpu->arch.nmi_pending ||
(kvm_arch_interrupt_allowed(vcpu) &&
}
EXPORT_SYMBOL_GPL(kvm_set_rflags);
+void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
+{
+ int r;
+
+ if ((vcpu->arch.mmu.direct_map != work->arch.direct_map) ||
+ is_error_page(work->page))
+ return;
+
+ r = kvm_mmu_reload(vcpu);
+ if (unlikely(r))
+ return;
+
+ if (!vcpu->arch.mmu.direct_map &&
+ work->arch.cr3 != vcpu->arch.mmu.get_cr3(vcpu))
+ return;
+
+ vcpu->arch.mmu.page_fault(vcpu, work->gva, 0, true);
+}
+
+static inline u32 kvm_async_pf_hash_fn(gfn_t gfn)
+{
+ return hash_32(gfn & 0xffffffff, order_base_2(ASYNC_PF_PER_VCPU));
+}
+
+static inline u32 kvm_async_pf_next_probe(u32 key)
+{
+ return (key + 1) & (roundup_pow_of_two(ASYNC_PF_PER_VCPU) - 1);
+}
+
+static void kvm_add_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ u32 key = kvm_async_pf_hash_fn(gfn);
+
+ while (vcpu->arch.apf.gfns[key] != ~0)
+ key = kvm_async_pf_next_probe(key);
+
+ vcpu->arch.apf.gfns[key] = gfn;
+}
+
+static u32 kvm_async_pf_gfn_slot(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ int i;
+ u32 key = kvm_async_pf_hash_fn(gfn);
+
+ for (i = 0; i < roundup_pow_of_two(ASYNC_PF_PER_VCPU) &&
+ (vcpu->arch.apf.gfns[key] != gfn &&
+ vcpu->arch.apf.gfns[key] != ~0); i++)
+ key = kvm_async_pf_next_probe(key);
+
+ return key;
+}
+
+bool kvm_find_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ return vcpu->arch.apf.gfns[kvm_async_pf_gfn_slot(vcpu, gfn)] == gfn;
+}
+
+static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
+{
+ u32 i, j, k;
+
+ i = j = kvm_async_pf_gfn_slot(vcpu, gfn);
+ while (true) {
+ vcpu->arch.apf.gfns[i] = ~0;
+ do {
+ j = kvm_async_pf_next_probe(j);
+ if (vcpu->arch.apf.gfns[j] == ~0)
+ return;
+ k = kvm_async_pf_hash_fn(vcpu->arch.apf.gfns[j]);
+ /*
+ * k lies cyclically in ]i,j]
+ * | i.k.j |
+ * |....j i.k.| or |.k..j i...|
+ */
+ } while ((i <= j) ? (i < k && k <= j) : (i < k || k <= j));
+ vcpu->arch.apf.gfns[i] = vcpu->arch.apf.gfns[j];
+ i = j;
+ }
+}
+
+static int apf_put_user(struct kvm_vcpu *vcpu, u32 val)
+{
+
+ return kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, &val,
+ sizeof(val));
+}
+
+void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+ struct x86_exception fault;
+
+ trace_kvm_async_pf_not_present(work->arch.token, work->gva);
+ kvm_add_async_pf_gfn(vcpu, work->arch.gfn);
+
+ if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) ||
+ (vcpu->arch.apf.send_user_only &&
+ kvm_x86_ops->get_cpl(vcpu) == 0))
+ kvm_make_request(KVM_REQ_APF_HALT, vcpu);
+ else if (!apf_put_user(vcpu, KVM_PV_REASON_PAGE_NOT_PRESENT)) {
+ fault.vector = PF_VECTOR;
+ fault.error_code_valid = true;
+ fault.error_code = 0;
+ fault.nested_page_fault = false;
+ fault.address = work->arch.token;
+ kvm_inject_page_fault(vcpu, &fault);
+ }
+}
+
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+ struct x86_exception fault;
+
+ trace_kvm_async_pf_ready(work->arch.token, work->gva);
+ if (is_error_page(work->page))
+ work->arch.token = ~0; /* broadcast wakeup */
+ else
+ kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+
+ if ((vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED) &&
+ !apf_put_user(vcpu, KVM_PV_REASON_PAGE_READY)) {
+ fault.vector = PF_VECTOR;
+ fault.error_code_valid = true;
+ fault.error_code = 0;
+ fault.nested_page_fault = false;
+ fault.address = work->arch.token;
+ kvm_inject_page_fault(vcpu, &fault);
+ }
+ vcpu->arch.apf.halted = false;
+}
+
+bool kvm_arch_can_inject_async_page_present(struct kvm_vcpu *vcpu)
+{
+ if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
+ return true;
+ else
+ return !kvm_event_needs_reinjection(vcpu) &&
+ kvm_x86_ops->interrupt_allowed(vcpu);
+}
+
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
projects / linux-flexiantxendom0-natty.git / blobdiff