* Copyright (C) 2006 Qumranet, Inc.
* Copyright (C) 2008 Qumranet, Inc.
* Copyright IBM Corporation, 2008
+ * Copyright 2010 Red Hat, Inc. and/or its affilates.
*
* Authors:
* Avi Kivity <avi@qumranet.com>
#include <linux/srcu.h>
#include <linux/slab.h>
#include <linux/perf_event.h>
+#include <linux/uaccess.h>
#include <trace/events/kvm.h>
#define CREATE_TRACE_POINTS
#include "trace.h"
#include <asm/debugreg.h>
-#include <asm/uaccess.h>
#include <asm/msr.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/mce.h>
+#include <asm/i387.h>
+#include <asm/xcr.h>
#define MAX_IO_MSRS 256
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
| X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \
| X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR \
+ | X86_CR4_OSXSAVE \
| X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
{ NULL }
};
+u64 __read_mostly host_xcr0;
+
+static inline u32 bit(int bitno)
+{
+ return 1 << (bitno & 31);
+}
+
static void kvm_on_user_return(struct user_return_notifier *urn)
{
unsigned slot;
prev_nr = vcpu->arch.exception.nr;
if (prev_nr == DF_VECTOR) {
/* triple fault -> shutdown */
- set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
return;
}
class1 = exception_class(prev_nr);
return changed;
}
-static int __kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
{
unsigned long old_cr0 = kvm_read_cr0(vcpu);
unsigned long update_bits = X86_CR0_PG | X86_CR0_WP |
kvm_mmu_reset_context(vcpu);
return 0;
}
+EXPORT_SYMBOL_GPL(kvm_set_cr0);
+
+void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
+{
+ (void)kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f));
+}
+EXPORT_SYMBOL_GPL(kvm_lmsw);
-void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
{
- if (__kvm_set_cr0(vcpu, cr0))
+ u64 xcr0;
+
+ /* Only support XCR_XFEATURE_ENABLED_MASK(xcr0) now */
+ if (index != XCR_XFEATURE_ENABLED_MASK)
+ return 1;
+ xcr0 = xcr;
+ if (kvm_x86_ops->get_cpl(vcpu) != 0)
+ return 1;
+ if (!(xcr0 & XSTATE_FP))
+ return 1;
+ if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
+ return 1;
+ if (xcr0 & ~host_xcr0)
+ return 1;
+ vcpu->arch.xcr0 = xcr0;
+ vcpu->guest_xcr0_loaded = 0;
+ return 0;
+}
+
+int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
+{
+ if (__kvm_set_xcr(vcpu, index, xcr)) {
kvm_inject_gp(vcpu, 0);
+ return 1;
+ }
+ return 0;
}
-EXPORT_SYMBOL_GPL(kvm_set_cr0);
+EXPORT_SYMBOL_GPL(kvm_set_xcr);
-void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw)
+static bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
{
- kvm_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~0x0eul) | (msw & 0x0f));
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 1, 0);
+ return best && (best->ecx & bit(X86_FEATURE_XSAVE));
}
-EXPORT_SYMBOL_GPL(kvm_lmsw);
-int __kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+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);
unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE;
if (cr4 & CR4_RESERVED_BITS)
return 1;
+ if (!guest_cpuid_has_xsave(vcpu) && (cr4 & X86_CR4_OSXSAVE))
+ return 1;
+
if (is_long_mode(vcpu)) {
if (!(cr4 & X86_CR4_PAE))
return 1;
if ((cr4 ^ old_cr4) & pdptr_bits)
kvm_mmu_reset_context(vcpu);
- return 0;
-}
+ if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
+ update_cpuid(vcpu);
-void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
-{
- if (__kvm_set_cr4(vcpu, cr4))
- kvm_inject_gp(vcpu, 0);
+ return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_cr4);
-static int __kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
+int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
{
if (cr3 == vcpu->arch.cr3 && !pdptrs_changed(vcpu)) {
kvm_mmu_sync_roots(vcpu);
vcpu->arch.mmu.new_cr3(vcpu);
return 0;
}
-
-void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
-{
- if (__kvm_set_cr3(vcpu, cr3))
- kvm_inject_gp(vcpu, 0);
-}
EXPORT_SYMBOL_GPL(kvm_set_cr3);
int __kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8)
}
EXPORT_SYMBOL_GPL(kvm_get_dr);
-static inline u32 bit(int bitno)
-{
- return 1 << (bitno & 31);
-}
-
/*
* List of msr numbers which we expose to userspace through KVM_GET_MSRS
* and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
HV_X64_MSR_GUEST_OS_ID, HV_X64_MSR_HYPERCALL,
HV_X64_MSR_APIC_ASSIST_PAGE,
MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
- MSR_K6_STAR,
+ MSR_STAR,
#ifdef CONFIG_X86_64
MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
#endif
static u32 emulated_msrs[] = {
MSR_IA32_MISC_ENABLE,
+ MSR_IA32_MCG_STATUS,
+ MSR_IA32_MCG_CTL,
};
static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
if (!vcpu->time_page)
return 0;
- set_bit(KVM_REQ_KVMCLOCK_UPDATE, &v->requests);
+ kvm_make_request(KVM_REQ_KVMCLOCK_UPDATE, v);
return 1;
}
case KVM_CAP_PCI_SEGMENT:
case KVM_CAP_DEBUGREGS:
case KVM_CAP_X86_ROBUST_SINGLESTEP:
+ case KVM_CAP_XSAVE:
r = 1;
break;
case KVM_CAP_COALESCED_MMIO:
case KVM_CAP_MCE:
r = KVM_MAX_MCE_BANKS;
break;
+ case KVM_CAP_XCRS:
+ r = cpu_has_xsave;
+ break;
default:
r = 0;
break;
return r;
}
+static void wbinvd_ipi(void *garbage)
+{
+ wbinvd();
+}
+
+static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
+{
+ return vcpu->kvm->arch.iommu_domain &&
+ !(vcpu->kvm->arch.iommu_flags & KVM_IOMMU_CACHE_COHERENCY);
+}
+
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
+ /* Address WBINVD may be executed by guest */
+ if (need_emulate_wbinvd(vcpu)) {
+ if (kvm_x86_ops->has_wbinvd_exit())
+ cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
+ else if (vcpu->cpu != -1 && vcpu->cpu != cpu)
+ smp_call_function_single(vcpu->cpu,
+ wbinvd_ipi, NULL, 1);
+ }
+
kvm_x86_ops->vcpu_load(vcpu, cpu);
if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) {
unsigned long khz = cpufreq_quick_get(cpu);
r = 0;
kvm_apic_set_version(vcpu);
kvm_x86_ops->cpuid_update(vcpu);
+ update_cpuid(vcpu);
out_free:
vfree(cpuid_entries);
vcpu->arch.cpuid_nent = cpuid->nent;
kvm_apic_set_version(vcpu);
kvm_x86_ops->cpuid_update(vcpu);
+ update_cpuid(vcpu);
return 0;
out:
0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW);
/* cpuid 1.ecx */
const u32 kvm_supported_word4_x86_features =
- F(XMM3) | 0 /* Reserved, DTES64, MONITOR */ |
+ F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ |
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, XSAVE, OSXSAVE */;
+ 0 /* Reserved, AES */ | F(XSAVE) | 0 /* OSXSAVE */ | F(AVX);
/* cpuid 0x80000001.ecx */
const u32 kvm_supported_word6_x86_features =
F(LAHF_LM) | F(CMP_LEGACY) | F(SVM) | 0 /* ExtApicSpace */ |
switch (function) {
case 0:
- entry->eax = min(entry->eax, (u32)0xb);
+ entry->eax = min(entry->eax, (u32)0xd);
break;
case 1:
entry->edx &= kvm_supported_word0_x86_features;
}
break;
}
+ case 0xd: {
+ int i;
+
+ entry->flags |= KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ for (i = 1; *nent < maxnent; ++i) {
+ if (entry[i - 1].eax == 0 && i != 2)
+ break;
+ do_cpuid_1_ent(&entry[i], function, i);
+ entry[i].flags |=
+ KVM_CPUID_FLAG_SIGNIFCANT_INDEX;
+ ++*nent;
+ }
+ break;
+ }
case KVM_CPUID_SIGNATURE: {
char signature[12] = "KVMKVMKVM\0\0";
u32 *sigptr = (u32 *)signature;
printk(KERN_DEBUG "kvm: set_mce: "
"injects mce exception while "
"previous one is in progress!\n");
- set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+ kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
return 0;
}
if (banks[1] & MCI_STATUS_VAL)
return 0;
}
+static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
+ struct kvm_xsave *guest_xsave)
+{
+ if (cpu_has_xsave)
+ memcpy(guest_xsave->region,
+ &vcpu->arch.guest_fpu.state->xsave,
+ sizeof(struct xsave_struct));
+ else {
+ memcpy(guest_xsave->region,
+ &vcpu->arch.guest_fpu.state->fxsave,
+ sizeof(struct i387_fxsave_struct));
+ *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)] =
+ XSTATE_FPSSE;
+ }
+}
+
+static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
+ struct kvm_xsave *guest_xsave)
+{
+ u64 xstate_bv =
+ *(u64 *)&guest_xsave->region[XSAVE_HDR_OFFSET / sizeof(u32)];
+
+ if (cpu_has_xsave)
+ memcpy(&vcpu->arch.guest_fpu.state->xsave,
+ guest_xsave->region, sizeof(struct xsave_struct));
+ else {
+ if (xstate_bv & ~XSTATE_FPSSE)
+ return -EINVAL;
+ memcpy(&vcpu->arch.guest_fpu.state->fxsave,
+ guest_xsave->region, sizeof(struct i387_fxsave_struct));
+ }
+ return 0;
+}
+
+static void kvm_vcpu_ioctl_x86_get_xcrs(struct kvm_vcpu *vcpu,
+ struct kvm_xcrs *guest_xcrs)
+{
+ if (!cpu_has_xsave) {
+ guest_xcrs->nr_xcrs = 0;
+ return;
+ }
+
+ guest_xcrs->nr_xcrs = 1;
+ guest_xcrs->flags = 0;
+ guest_xcrs->xcrs[0].xcr = XCR_XFEATURE_ENABLED_MASK;
+ guest_xcrs->xcrs[0].value = vcpu->arch.xcr0;
+}
+
+static int kvm_vcpu_ioctl_x86_set_xcrs(struct kvm_vcpu *vcpu,
+ struct kvm_xcrs *guest_xcrs)
+{
+ int i, r = 0;
+
+ if (!cpu_has_xsave)
+ return -EINVAL;
+
+ if (guest_xcrs->nr_xcrs > KVM_MAX_XCRS || guest_xcrs->flags)
+ return -EINVAL;
+
+ for (i = 0; i < guest_xcrs->nr_xcrs; i++)
+ /* Only support XCR0 currently */
+ if (guest_xcrs->xcrs[0].xcr == XCR_XFEATURE_ENABLED_MASK) {
+ r = __kvm_set_xcr(vcpu, XCR_XFEATURE_ENABLED_MASK,
+ guest_xcrs->xcrs[0].value);
+ break;
+ }
+ if (r)
+ r = -EINVAL;
+ return r;
+}
+
long kvm_arch_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
int r;
- struct kvm_lapic_state *lapic = NULL;
+ union {
+ struct kvm_lapic_state *lapic;
+ struct kvm_xsave *xsave;
+ struct kvm_xcrs *xcrs;
+ void *buffer;
+ } u;
+ u.buffer = NULL;
switch (ioctl) {
case KVM_GET_LAPIC: {
r = -EINVAL;
if (!vcpu->arch.apic)
goto out;
- lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
+ u.lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
r = -ENOMEM;
- if (!lapic)
+ if (!u.lapic)
goto out;
- r = kvm_vcpu_ioctl_get_lapic(vcpu, lapic);
+ r = kvm_vcpu_ioctl_get_lapic(vcpu, u.lapic);
if (r)
goto out;
r = -EFAULT;
- if (copy_to_user(argp, lapic, sizeof(struct kvm_lapic_state)))
+ if (copy_to_user(argp, u.lapic, sizeof(struct kvm_lapic_state)))
goto out;
r = 0;
break;
r = -EINVAL;
if (!vcpu->arch.apic)
goto out;
- lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
+ u.lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
r = -ENOMEM;
- if (!lapic)
+ if (!u.lapic)
goto out;
r = -EFAULT;
- if (copy_from_user(lapic, argp, sizeof(struct kvm_lapic_state)))
+ if (copy_from_user(u.lapic, argp, sizeof(struct kvm_lapic_state)))
goto out;
- r = kvm_vcpu_ioctl_set_lapic(vcpu, lapic);
+ r = kvm_vcpu_ioctl_set_lapic(vcpu, u.lapic);
if (r)
goto out;
r = 0;
r = kvm_vcpu_ioctl_x86_set_debugregs(vcpu, &dbgregs);
break;
}
+ case KVM_GET_XSAVE: {
+ u.xsave = kzalloc(sizeof(struct kvm_xsave), GFP_KERNEL);
+ r = -ENOMEM;
+ if (!u.xsave)
+ break;
+
+ kvm_vcpu_ioctl_x86_get_xsave(vcpu, u.xsave);
+
+ r = -EFAULT;
+ if (copy_to_user(argp, u.xsave, sizeof(struct kvm_xsave)))
+ break;
+ r = 0;
+ 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;
+
+ r = kvm_vcpu_ioctl_x86_set_xsave(vcpu, u.xsave);
+ break;
+ }
+ case KVM_GET_XCRS: {
+ u.xcrs = kzalloc(sizeof(struct kvm_xcrs), GFP_KERNEL);
+ r = -ENOMEM;
+ if (!u.xcrs)
+ break;
+
+ kvm_vcpu_ioctl_x86_get_xcrs(vcpu, u.xcrs);
+
+ r = -EFAULT;
+ if (copy_to_user(argp, u.xcrs,
+ sizeof(struct kvm_xcrs)))
+ break;
+ r = 0;
+ 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;
+
+ r = kvm_vcpu_ioctl_x86_set_xcrs(vcpu, u.xcrs);
+ break;
+ }
default:
r = -EINVAL;
}
out:
- kfree(lapic);
+ kfree(u.buffer);
return r;
}
return kvm->arch.n_alloc_mmu_pages;
}
-gfn_t unalias_gfn_instantiation(struct kvm *kvm, gfn_t gfn)
-{
- int i;
- struct kvm_mem_alias *alias;
- struct kvm_mem_aliases *aliases;
-
- aliases = kvm_aliases(kvm);
-
- for (i = 0; i < aliases->naliases; ++i) {
- alias = &aliases->aliases[i];
- if (alias->flags & KVM_ALIAS_INVALID)
- continue;
- if (gfn >= alias->base_gfn
- && gfn < alias->base_gfn + alias->npages)
- return alias->target_gfn + gfn - alias->base_gfn;
- }
- return gfn;
-}
-
-gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
-{
- int i;
- struct kvm_mem_alias *alias;
- struct kvm_mem_aliases *aliases;
-
- aliases = kvm_aliases(kvm);
-
- for (i = 0; i < aliases->naliases; ++i) {
- alias = &aliases->aliases[i];
- if (gfn >= alias->base_gfn
- && gfn < alias->base_gfn + alias->npages)
- return alias->target_gfn + gfn - alias->base_gfn;
- }
- return gfn;
-}
-
-/*
- * Set a new alias region. Aliases map a portion of physical memory into
- * another portion. This is useful for memory windows, for example the PC
- * VGA region.
- */
-static int kvm_vm_ioctl_set_memory_alias(struct kvm *kvm,
- struct kvm_memory_alias *alias)
-{
- int r, n;
- struct kvm_mem_alias *p;
- struct kvm_mem_aliases *aliases, *old_aliases;
-
- r = -EINVAL;
- /* General sanity checks */
- if (alias->memory_size & (PAGE_SIZE - 1))
- goto out;
- if (alias->guest_phys_addr & (PAGE_SIZE - 1))
- goto out;
- if (alias->slot >= KVM_ALIAS_SLOTS)
- goto out;
- if (alias->guest_phys_addr + alias->memory_size
- < alias->guest_phys_addr)
- goto out;
- if (alias->target_phys_addr + alias->memory_size
- < alias->target_phys_addr)
- goto out;
-
- r = -ENOMEM;
- aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
- if (!aliases)
- goto out;
-
- mutex_lock(&kvm->slots_lock);
-
- /* invalidate any gfn reference in case of deletion/shrinking */
- memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases));
- aliases->aliases[alias->slot].flags |= KVM_ALIAS_INVALID;
- old_aliases = kvm->arch.aliases;
- rcu_assign_pointer(kvm->arch.aliases, aliases);
- synchronize_srcu_expedited(&kvm->srcu);
- kvm_mmu_zap_all(kvm);
- kfree(old_aliases);
-
- r = -ENOMEM;
- aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
- if (!aliases)
- goto out_unlock;
-
- memcpy(aliases, kvm->arch.aliases, sizeof(struct kvm_mem_aliases));
-
- p = &aliases->aliases[alias->slot];
- p->base_gfn = alias->guest_phys_addr >> PAGE_SHIFT;
- p->npages = alias->memory_size >> PAGE_SHIFT;
- p->target_gfn = alias->target_phys_addr >> PAGE_SHIFT;
- p->flags &= ~(KVM_ALIAS_INVALID);
-
- for (n = KVM_ALIAS_SLOTS; n > 0; --n)
- if (aliases->aliases[n - 1].npages)
- break;
- aliases->naliases = n;
-
- old_aliases = kvm->arch.aliases;
- rcu_assign_pointer(kvm->arch.aliases, aliases);
- synchronize_srcu_expedited(&kvm->srcu);
- kfree(old_aliases);
- r = 0;
-
-out_unlock:
- mutex_unlock(&kvm->slots_lock);
-out:
- return r;
-}
-
static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
int r;
union {
struct kvm_pit_state ps;
struct kvm_pit_state2 ps2;
- struct kvm_memory_alias alias;
struct kvm_pit_config pit_config;
} u;
goto out;
break;
}
- case KVM_SET_MEMORY_REGION: {
- struct kvm_memory_region kvm_mem;
- struct kvm_userspace_memory_region kvm_userspace_mem;
-
- r = -EFAULT;
- if (copy_from_user(&kvm_mem, argp, sizeof kvm_mem))
- goto out;
- kvm_userspace_mem.slot = kvm_mem.slot;
- kvm_userspace_mem.flags = kvm_mem.flags;
- kvm_userspace_mem.guest_phys_addr = kvm_mem.guest_phys_addr;
- kvm_userspace_mem.memory_size = kvm_mem.memory_size;
- r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 0);
- if (r)
- goto out;
- break;
- }
case KVM_SET_NR_MMU_PAGES:
r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg);
if (r)
case KVM_GET_NR_MMU_PAGES:
r = kvm_vm_ioctl_get_nr_mmu_pages(kvm);
break;
- case KVM_SET_MEMORY_ALIAS:
- r = -EFAULT;
- if (copy_from_user(&u.alias, argp, sizeof(struct kvm_memory_alias)))
- goto out;
- r = kvm_vm_ioctl_set_memory_alias(kvm, &u.alias);
- if (r)
- goto out;
- break;
case KVM_CREATE_IRQCHIP: {
struct kvm_pic *vpic;
goto emul_write;
page = gfn_to_page(vcpu->kvm, gpa >> PAGE_SHIFT);
+ if (is_error_page(page)) {
+ kvm_release_page_clean(page);
+ goto emul_write;
+ }
kaddr = kmap_atomic(page, KM_USER0);
kaddr += offset_in_page(gpa);
return X86EMUL_CONTINUE;
}
+int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu)
+{
+ if (!need_emulate_wbinvd(vcpu))
+ return X86EMUL_CONTINUE;
+
+ if (kvm_x86_ops->has_wbinvd_exit()) {
+ smp_call_function_many(vcpu->arch.wbinvd_dirty_mask,
+ wbinvd_ipi, NULL, 1);
+ cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
+ }
+ wbinvd();
+ return X86EMUL_CONTINUE;
+}
+EXPORT_SYMBOL_GPL(kvm_emulate_wbinvd);
+
int emulate_clts(struct kvm_vcpu *vcpu)
{
kvm_x86_ops->set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
switch (cr) {
case 0:
- res = __kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
+ res = kvm_set_cr0(vcpu, mk_cr_64(kvm_read_cr0(vcpu), val));
break;
case 2:
vcpu->arch.cr2 = val;
break;
case 3:
- res = __kvm_set_cr3(vcpu, val);
+ res = kvm_set_cr3(vcpu, val);
break;
case 4:
- res = __kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
+ res = kvm_set_cr4(vcpu, mk_cr_64(kvm_read_cr4(vcpu), val));
break;
case 8:
res = __kvm_set_cr8(vcpu, val & 0xfUL);
return EMULATE_FAIL;
}
+static bool reexecute_instruction(struct kvm_vcpu *vcpu, gva_t gva)
+{
+ gpa_t gpa;
+
+ if (tdp_enabled)
+ return false;
+
+ /*
+ * if emulation was due to access to shadowed page table
+ * and it failed try to unshadow page and re-entetr the
+ * guest to let CPU execute the instruction.
+ */
+ if (kvm_mmu_unprotect_page_virt(vcpu, gva))
+ return true;
+
+ gpa = kvm_mmu_gva_to_gpa_system(vcpu, gva, NULL);
+
+ if (gpa == UNMAPPED_GVA)
+ return true; /* let cpu generate fault */
+
+ if (!kvm_is_error_hva(gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT)))
+ return true;
+
+ return false;
+}
+
int emulate_instruction(struct kvm_vcpu *vcpu,
unsigned long cr2,
u16 error_code,
++vcpu->stat.insn_emulation;
if (r) {
- if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
+ if (reexecute_instruction(vcpu, cr2))
return EMULATE_DONE;
if (emulation_type & EMULTYPE_SKIP)
return EMULATE_FAIL;
r = x86_emulate_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
if (r) { /* emulation failed */
- /*
- * if emulation was due to access to shadowed page table
- * and it failed try to unshadow page and re-entetr the
- * guest to let CPU execute the instruction.
- */
- if (kvm_mmu_unprotect_page_virt(vcpu, cr2))
+ if (reexecute_instruction(vcpu, cr2))
return EMULATE_DONE;
return handle_emulation_failure(vcpu);
perf_register_guest_info_callbacks(&kvm_guest_cbs);
+ if (cpu_has_xsave)
+ host_xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
+
return 0;
out:
}
}
+static void kvm_load_guest_xcr0(struct kvm_vcpu *vcpu)
+{
+ if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE) &&
+ !vcpu->guest_xcr0_loaded) {
+ /* kvm_set_xcr() also depends on this */
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, vcpu->arch.xcr0);
+ vcpu->guest_xcr0_loaded = 1;
+ }
+}
+
+static void kvm_put_guest_xcr0(struct kvm_vcpu *vcpu)
+{
+ if (vcpu->guest_xcr0_loaded) {
+ if (vcpu->arch.xcr0 != host_xcr0)
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, host_xcr0);
+ vcpu->guest_xcr0_loaded = 0;
+ }
+}
+
static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
{
int r;
bool req_int_win = !irqchip_in_kernel(vcpu->kvm) &&
vcpu->run->request_interrupt_window;
- if (vcpu->requests)
- if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
- kvm_mmu_unload(vcpu);
-
- r = kvm_mmu_reload(vcpu);
- if (unlikely(r))
- goto out;
-
if (vcpu->requests) {
- if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
+ if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
+ kvm_mmu_unload(vcpu);
+ if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))
__kvm_migrate_timers(vcpu);
- if (test_and_clear_bit(KVM_REQ_KVMCLOCK_UPDATE, &vcpu->requests))
+ if (kvm_check_request(KVM_REQ_KVMCLOCK_UPDATE, vcpu))
kvm_write_guest_time(vcpu);
- if (test_and_clear_bit(KVM_REQ_MMU_SYNC, &vcpu->requests))
+ if (kvm_check_request(KVM_REQ_MMU_SYNC, vcpu))
kvm_mmu_sync_roots(vcpu);
- if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+ if (kvm_check_request(KVM_REQ_TLB_FLUSH, vcpu))
kvm_x86_ops->tlb_flush(vcpu);
- if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
- &vcpu->requests)) {
+ if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
r = 0;
goto out;
}
- if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) {
+ if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
r = 0;
goto out;
}
- if (test_and_clear_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests)) {
+ if (kvm_check_request(KVM_REQ_DEACTIVATE_FPU, vcpu)) {
vcpu->fpu_active = 0;
kvm_x86_ops->fpu_deactivate(vcpu);
}
}
+ r = kvm_mmu_reload(vcpu);
+ if (unlikely(r))
+ goto out;
+
preempt_disable();
kvm_x86_ops->prepare_guest_switch(vcpu);
if (vcpu->fpu_active)
kvm_load_guest_fpu(vcpu);
+ kvm_load_guest_xcr0(vcpu);
atomic_set(&vcpu->guest_mode, 1);
smp_wmb();
srcu_read_unlock(&kvm->srcu, vcpu->srcu_idx);
kvm_vcpu_block(vcpu);
vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
- if (test_and_clear_bit(KVM_REQ_UNHALT, &vcpu->requests))
+ if (kvm_check_request(KVM_REQ_UNHALT, vcpu))
{
switch(vcpu->arch.mp_state) {
case KVM_MP_STATE_HALTED:
return r;
}
-/*
- * fxsave fpu state. Taken from x86_64/processor.h. To be killed when
- * we have asm/x86/processor.h
- */
-struct fxsave {
- u16 cwd;
- u16 swd;
- u16 twd;
- u16 fop;
- u64 rip;
- u64 rdp;
- u32 mxcsr;
- u32 mxcsr_mask;
- u32 st_space[32]; /* 8*16 bytes for each FP-reg = 128 bytes */
-#ifdef CONFIG_X86_64
- u32 xmm_space[64]; /* 16*16 bytes for each XMM-reg = 256 bytes */
-#else
- u32 xmm_space[32]; /* 8*16 bytes for each XMM-reg = 128 bytes */
-#endif
-};
-
/*
* Translate a guest virtual address to a guest physical address.
*/
int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image;
+ struct i387_fxsave_struct *fxsave =
+ &vcpu->arch.guest_fpu.state->fxsave;
memcpy(fpu->fpr, fxsave->st_space, 128);
fpu->fcw = fxsave->cwd;
int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
- struct fxsave *fxsave = (struct fxsave *)&vcpu->arch.guest_fx_image;
+ struct i387_fxsave_struct *fxsave =
+ &vcpu->arch.guest_fpu.state->fxsave;
memcpy(fxsave->st_space, fpu->fpr, 128);
fxsave->cwd = fpu->fcw;
return 0;
}
-void fx_init(struct kvm_vcpu *vcpu)
+int fx_init(struct kvm_vcpu *vcpu)
{
- unsigned after_mxcsr_mask;
+ int err;
+
+ err = fpu_alloc(&vcpu->arch.guest_fpu);
+ if (err)
+ return err;
+
+ fpu_finit(&vcpu->arch.guest_fpu);
/*
- * Touch the fpu the first time in non atomic context as if
- * this is the first fpu instruction the exception handler
- * will fire before the instruction returns and it'll have to
- * allocate ram with GFP_KERNEL.
+ * Ensure guest xcr0 is valid for loading
*/
- if (!used_math())
- kvm_fx_save(&vcpu->arch.host_fx_image);
-
- /* Initialize guest FPU by resetting ours and saving into guest's */
- preempt_disable();
- kvm_fx_save(&vcpu->arch.host_fx_image);
- kvm_fx_finit();
- kvm_fx_save(&vcpu->arch.guest_fx_image);
- kvm_fx_restore(&vcpu->arch.host_fx_image);
- preempt_enable();
+ vcpu->arch.xcr0 = XSTATE_FP;
vcpu->arch.cr0 |= X86_CR0_ET;
- after_mxcsr_mask = offsetof(struct i387_fxsave_struct, st_space);
- vcpu->arch.guest_fx_image.mxcsr = 0x1f80;
- memset((void *)&vcpu->arch.guest_fx_image + after_mxcsr_mask,
- 0, sizeof(struct i387_fxsave_struct) - after_mxcsr_mask);
+
+ return 0;
}
EXPORT_SYMBOL_GPL(fx_init);
+static void fx_free(struct kvm_vcpu *vcpu)
+{
+ fpu_free(&vcpu->arch.guest_fpu);
+}
+
void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
if (vcpu->guest_fpu_loaded)
return;
+ /*
+ * Restore all possible states in the guest,
+ * and assume host would use all available bits.
+ * Guest xcr0 would be loaded later.
+ */
+ kvm_put_guest_xcr0(vcpu);
vcpu->guest_fpu_loaded = 1;
- kvm_fx_save(&vcpu->arch.host_fx_image);
- kvm_fx_restore(&vcpu->arch.guest_fx_image);
+ unlazy_fpu(current);
+ fpu_restore_checking(&vcpu->arch.guest_fpu);
trace_kvm_fpu(1);
}
void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
{
+ kvm_put_guest_xcr0(vcpu);
+
if (!vcpu->guest_fpu_loaded)
return;
vcpu->guest_fpu_loaded = 0;
- kvm_fx_save(&vcpu->arch.guest_fx_image);
- kvm_fx_restore(&vcpu->arch.host_fx_image);
+ fpu_save_init(&vcpu->arch.guest_fpu);
++vcpu->stat.fpu_reload;
- set_bit(KVM_REQ_DEACTIVATE_FPU, &vcpu->requests);
+ kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
trace_kvm_fpu(0);
}
vcpu->arch.time_page = NULL;
}
+ free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
+ fx_free(vcpu);
kvm_x86_ops->vcpu_free(vcpu);
}
{
int r;
- /* We do fxsave: this must be aligned. */
- BUG_ON((unsigned long)&vcpu->arch.host_fx_image & 0xF);
-
vcpu->arch.mtrr_state.have_fixed = 1;
vcpu_load(vcpu);
r = kvm_arch_vcpu_reset(vcpu);
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
+ fx_free(vcpu);
kvm_x86_ops->vcpu_free(vcpu);
}
}
vcpu->arch.mcg_cap = KVM_MAX_MCE_BANKS;
+ if (!zalloc_cpumask_var(&vcpu->arch.wbinvd_dirty_mask, GFP_KERNEL))
+ goto fail_free_mce_banks;
+
return 0;
+fail_free_mce_banks:
+ kfree(vcpu->arch.mce_banks);
fail_free_lapic:
kvm_free_lapic(vcpu);
fail_mmu_destroy:
if (!kvm)
return ERR_PTR(-ENOMEM);
- kvm->arch.aliases = kzalloc(sizeof(struct kvm_mem_aliases), GFP_KERNEL);
- if (!kvm->arch.aliases) {
- kfree(kvm);
- return ERR_PTR(-ENOMEM);
- }
-
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.assigned_dev_head);
void kvm_arch_sync_events(struct kvm *kvm)
{
kvm_free_all_assigned_devices(kvm);
+ kvm_free_pit(kvm);
}
void kvm_arch_destroy_vm(struct kvm *kvm)
{
kvm_iommu_unmap_guest(kvm);
- kvm_free_pit(kvm);
kfree(kvm->arch.vpic);
kfree(kvm->arch.vioapic);
kvm_free_vcpus(kvm);
if (kvm->arch.ept_identity_pagetable)
put_page(kvm->arch.ept_identity_pagetable);
cleanup_srcu_struct(&kvm->srcu);
- kfree(kvm->arch.aliases);
kfree(kvm);
}
int user_alloc)
{
int npages = memslot->npages;
+ int map_flags = MAP_PRIVATE | MAP_ANONYMOUS;
+
+ /* Prevent internal slot pages from being moved by fork()/COW. */
+ if (memslot->id >= KVM_MEMORY_SLOTS)
+ map_flags = MAP_SHARED | MAP_ANONYMOUS;
/*To keep backward compatibility with older userspace,
*x86 needs to hanlde !user_alloc case.
userspace_addr = do_mmap(NULL, 0,
npages * PAGE_SIZE,
PROT_READ | PROT_WRITE,
- MAP_PRIVATE | MAP_ANONYMOUS,
+ map_flags,
0);
up_write(¤t->mm->mmap_sem);