#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
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)
* 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)
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) {
}
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_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
case KVM_CAP_XSAVE:
+ case KVM_CAP_ASYNC_PF:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
!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))
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)))
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);
#ifdef CONFIG_CPU_FREQ
struct cpufreq_policy policy;
memset(&policy, 0, sizeof(policy));
- cpufreq_get_policy(&policy, get_cpu());
+ 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);
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);
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;
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);
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);
}
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);
/*
* 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);
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 || is_error_page(work->page))
+ return;
+
+ r = kvm_mmu_reload(vcpu);
+ if (unlikely(r))
+ 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)
+{
+ 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)) {
+ vcpu->arch.fault.error_code = 0;
+ vcpu->arch.fault.address = work->arch.token;
+ kvm_inject_page_fault(vcpu);
+ }
+}
+
+void kvm_arch_async_page_present(struct kvm_vcpu *vcpu,
+ struct kvm_async_pf *work)
+{
+ 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)) {
+ vcpu->arch.fault.error_code = 0;
+ vcpu->arch.fault.address = work->arch.token;
+ kvm_inject_page_fault(vcpu);
+ }
+}
+
+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);