#include <linux/pvclock_gtod.h>
#include <linux/kvm_irqfd.h>
#include <linux/irqbypass.h>
+#include <linux/nospec.h>
#include <trace/events/kvm.h>
#define CREATE_TRACE_POINTS
struct kvm_shared_msrs *locals
= container_of(urn, struct kvm_shared_msrs, urn);
struct kvm_shared_msr_values *values;
+ unsigned long flags;
+ /*
+ * Disabling irqs at this point since the following code could be
+ * interrupted and executed through kvm_arch_hardware_disable()
+ */
+ local_irq_save(flags);
+ if (locals->registered) {
+ locals->registered = false;
+ user_return_notifier_unregister(urn);
+ }
+ local_irq_restore(flags);
for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
values = &locals->values[slot];
if (values->host != values->curr) {
values->curr = values->host;
}
}
- locals->registered = false;
- user_return_notifier_unregister(urn);
}
static void shared_msr_update(unsigned slot, u32 msr)
struct kvm_shared_msrs *smsr = per_cpu_ptr(shared_msrs, cpu);
int err;
- if (((value ^ smsr->values[slot].curr) & mask) == 0)
+ value = (value & mask) | (smsr->values[slot].host & ~mask);
+ if (value == smsr->values[slot].curr)
return 0;
- smsr->values[slot].curr = value;
err = wrmsrl_safe(shared_msrs_global.msrs[slot], value);
if (err)
return 1;
+ smsr->values[slot].curr = value;
if (!smsr->registered) {
smsr->urn.on_user_return = kvm_on_user_return;
user_return_notifier_register(&smsr->urn);
data, offset, len, access);
}
+static inline u64 pdptr_rsvd_bits(struct kvm_vcpu *vcpu)
+{
+ return rsvd_bits(cpuid_maxphyaddr(vcpu), 63) | rsvd_bits(5, 8) |
+ rsvd_bits(1, 2);
+}
+
/*
- * Load the pae pdptrs. Return true is they are all valid.
+ * Load the pae pdptrs. Return 1 if they are all valid, 0 otherwise.
*/
int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3)
{
}
for (i = 0; i < ARRAY_SIZE(pdpte); ++i) {
if (is_present_gpte(pdpte[i]) &&
- (pdpte[i] &
- vcpu->arch.mmu.guest_rsvd_check.rsvd_bits_mask[0][2])) {
+ (pdpte[i] & pdptr_rsvd_bits(vcpu))) {
ret = 0;
goto out;
}
gfn_t gfn;
int r;
- if (is_long_mode(vcpu) || !is_pae(vcpu))
+ if (is_long_mode(vcpu) || !is_pae(vcpu) || !is_paging(vcpu))
return false;
if (!test_bit(VCPU_EXREG_PDPTR,
return 1;
/* PCID can not be enabled when cr3[11:0]!=000H or EFER.LMA=0 */
- if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_MASK) || !is_long_mode(vcpu))
+ if ((kvm_read_cr3(vcpu) & X86_CR3_PCID_ASID_MASK) ||
+ !is_long_mode(vcpu))
return 1;
}
static int __kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val)
{
+ size_t size = ARRAY_SIZE(vcpu->arch.db);
+
switch (dr) {
case 0 ... 3:
- vcpu->arch.db[dr] = val;
+ vcpu->arch.db[array_index_nospec(dr, size)] = val;
if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
vcpu->arch.eff_db[dr] = val;
break;
int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val)
{
+ size_t size = ARRAY_SIZE(vcpu->arch.db);
+
switch (dr) {
case 0 ... 3:
- *val = vcpu->arch.db[dr];
+ *val = vcpu->arch.db[array_index_nospec(dr, size)];
break;
case 4:
/* fall through */
#endif
MSR_IA32_TSC, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA,
MSR_IA32_FEATURE_CONTROL, MSR_IA32_BNDCFGS, MSR_TSC_AUX,
+ MSR_IA32_SPEC_CTRL, MSR_IA32_ARCH_CAPABILITIES
};
static unsigned num_msrs_to_save;
MSR_IA32_MCG_STATUS,
MSR_IA32_MCG_CTL,
MSR_IA32_SMBASE,
+ MSR_AMD64_VIRT_SPEC_CTRL,
};
static unsigned num_emulated_msrs;
-bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+u64 kvm_get_arch_capabilities(void)
{
- if (efer & efer_reserved_bits)
- return false;
+ u64 data;
+
+ rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
+
+ if (!boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
+ data |= ARCH_CAP_RDCL_NO;
+ if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ data |= ARCH_CAP_SSB_NO;
+ if (!boot_cpu_has_bug(X86_BUG_MDS))
+ data |= ARCH_CAP_MDS_NO;
+ /*
+ * On TAA affected systems, export MDS_NO=0 when:
+ * - TSX is enabled on the host, i.e. X86_FEATURE_RTM=1.
+ * - Updated microcode is present. This is detected by
+ * the presence of ARCH_CAP_TSX_CTRL_MSR and ensures
+ * that VERW clears CPU buffers.
+ *
+ * When MDS_NO=0 is exported, guests deploy clear CPU buffer
+ * mitigation and don't complain:
+ *
+ * "Vulnerable: Clear CPU buffers attempted, no microcode"
+ *
+ * If TSX is disabled on the system, guests are also mitigated against
+ * TAA and clear CPU buffer mitigation is not required for guests.
+ */
+ if (!boot_cpu_has(X86_FEATURE_RTM))
+ data &= ~ARCH_CAP_TAA_NO;
+ else if (!boot_cpu_has_bug(X86_BUG_TAA))
+ data |= ARCH_CAP_TAA_NO;
+ else if (data & ARCH_CAP_TSX_CTRL_MSR)
+ data &= ~ARCH_CAP_MDS_NO;
+
+ /* KVM does not emulate MSR_IA32_TSX_CTRL. */
+ data &= ~ARCH_CAP_TSX_CTRL_MSR;
+ return data;
+}
+
+EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
+
+static bool __kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
if (efer & EFER_FFXSR) {
struct kvm_cpuid_entry2 *feat;
}
return true;
+
+}
+bool kvm_valid_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+ if (efer & efer_reserved_bits)
+ return false;
+
+ return __kvm_valid_efer(vcpu, efer);
}
EXPORT_SYMBOL_GPL(kvm_valid_efer);
-static int set_efer(struct kvm_vcpu *vcpu, u64 efer)
+static int set_efer(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
{
u64 old_efer = vcpu->arch.efer;
+ u64 efer = msr_info->data;
- if (!kvm_valid_efer(vcpu, efer))
+ if (efer & efer_reserved_bits)
return 1;
- if (is_paging(vcpu)
- && (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
- return 1;
+ if (!msr_info->host_initiated) {
+ if (!__kvm_valid_efer(vcpu, efer))
+ return 1;
+
+ if (is_paging(vcpu) &&
+ (vcpu->arch.efer & EFER_LME) != (efer & EFER_LME))
+ return 1;
+ }
efer &= ~EFER_LMA;
efer |= vcpu->arch.efer & EFER_LMA;
vcpu->arch.tsc_always_catchup = 1;
return 0;
} else {
- WARN(1, "user requested TSC rate below hardware speed\n");
+ pr_warn_ratelimited("user requested TSC rate below hardware speed\n");
return -1;
}
}
user_tsc_khz, tsc_khz);
if (ratio == 0 || ratio >= kvm_max_tsc_scaling_ratio) {
- WARN_ONCE(1, "Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
- user_tsc_khz);
+ pr_warn_ratelimited("Invalid TSC scaling ratio - virtual-tsc-khz=%u\n",
+ user_tsc_khz);
return -1;
}
*/
BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
+ if (guest_hv_clock.version & 1)
+ ++guest_hv_clock.version; /* first time write, random junk */
+
vcpu->hv_clock.version = guest_hv_clock.version + 1;
kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
&vcpu->hv_clock,
default:
if (msr >= MSR_IA32_MC0_CTL &&
msr < MSR_IA32_MCx_CTL(bank_num)) {
- u32 offset = msr - MSR_IA32_MC0_CTL;
+ u32 offset = array_index_nospec(
+ msr - MSR_IA32_MC0_CTL,
+ MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
/* only 0 or all 1s can be written to IA32_MCi_CTL
* some Linux kernels though clear bit 10 in bank 4 to
* workaround a BIOS/GART TBL issue on AMD K8s, ignore
case MSR_AMD64_BU_CFG2:
break;
+ case MSR_IA32_ARCH_CAPABILITIES:
+ if (!msr_info->host_initiated)
+ return 1;
+ vcpu->arch.arch_capabilities = data;
+ break;
case MSR_EFER:
- return set_efer(vcpu, data);
+ return set_efer(vcpu, msr_info);
case MSR_K7_HWCR:
data &= ~(u64)0x40; /* ignore flush filter disable */
data &= ~(u64)0x100; /* ignore ignne emulation enable */
default:
if (msr >= MSR_IA32_MC0_CTL &&
msr < MSR_IA32_MCx_CTL(bank_num)) {
- u32 offset = msr - MSR_IA32_MC0_CTL;
+ u32 offset = array_index_nospec(
+ msr - MSR_IA32_MC0_CTL,
+ MSR_IA32_MCx_CTL(bank_num) - MSR_IA32_MC0_CTL);
+
data = vcpu->arch.mce_banks[offset];
break;
}
case MSR_IA32_UCODE_REV:
msr_info->data = 0x100000000ULL;
break;
+ case MSR_IA32_ARCH_CAPABILITIES:
+ if (!msr_info->host_initiated &&
+ !guest_cpuid_has_arch_capabilities(vcpu))
+ return 1;
+ msr_info->data = vcpu->arch.arch_capabilities;
+ break;
case MSR_MTRRcap:
case 0x200 ... 0x2ff:
return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
* fringe case that is not enabled except via specific settings
* of the module parameters.
*/
- r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
+ r = kvm_x86_ops->has_emulated_msr(MSR_IA32_SMBASE);
break;
case KVM_CAP_COALESCED_MMIO:
r = KVM_COALESCED_MMIO_PAGE_OFFSET;
}
kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
- vcpu->arch.switch_db_regs |= KVM_DEBUGREG_RELOAD;
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
kvm_x86_ops->vcpu_put(vcpu);
kvm_put_guest_fpu(vcpu);
vcpu->arch.last_host_tsc = rdtsc();
+ /*
+ * If userspace has set any breakpoints or watchpoints, dr6 is restored
+ * on every vmexit, but if not, we might have a stale dr6 from the
+ * guest. do_debug expects dr6 to be cleared after it runs, do the same.
+ */
+ set_debugreg(0, 6);
}
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
memset(&events->reserved, 0, sizeof(events->reserved));
}
+static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags);
+
static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
struct kvm_vcpu_events *events)
{
| KVM_VCPUEVENT_VALID_SMM))
return -EINVAL;
+ if (events->exception.injected &&
+ (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
+ return -EINVAL;
+
+ /* INITs are latched while in SMM */
+ if (events->flags & KVM_VCPUEVENT_VALID_SMM &&
+ (events->smi.smm || events->smi.pending) &&
+ vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
+ return -EINVAL;
+
process_nmi(vcpu);
vcpu->arch.exception.pending = events->exception.injected;
vcpu->arch.exception.nr = events->exception.nr;
vcpu->arch.apic->sipi_vector = events->sipi_vector;
if (events->flags & KVM_VCPUEVENT_VALID_SMM) {
+ u32 hflags = vcpu->arch.hflags;
if (events->smi.smm)
- vcpu->arch.hflags |= HF_SMM_MASK;
+ hflags |= HF_SMM_MASK;
else
- vcpu->arch.hflags &= ~HF_SMM_MASK;
+ hflags &= ~HF_SMM_MASK;
+ kvm_set_hflags(vcpu, hflags);
+
vcpu->arch.smi_pending = events->smi.pending;
if (events->smi.smm_inside_nmi)
vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
if (dbgregs->flags)
return -EINVAL;
+ if (dbgregs->dr6 & ~0xffffffffull)
+ return -EINVAL;
+ if (dbgregs->dr7 & ~0xffffffffull)
+ return -EINVAL;
+
memcpy(vcpu->arch.db, dbgregs->db, sizeof(vcpu->arch.db));
kvm_update_dr0123(vcpu);
vcpu->arch.dr6 = dbgregs->dr6;
memcpy(dest, xsave, XSAVE_HDR_OFFSET);
/* Set XSTATE_BV */
+ xstate_bv &= vcpu->arch.guest_supported_xcr0 | XFEATURE_MASK_FPSSE;
*(u64 *)(dest + XSAVE_HDR_OFFSET) = xstate_bv;
/*
}
}
+#define XSAVE_MXCSR_OFFSET 24
+
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)];
+ u32 mxcsr = *(u32 *)&guest_xsave->region[XSAVE_MXCSR_OFFSET / sizeof(u32)];
if (cpu_has_xsave) {
/*
* CPUID leaf 0xD, index 0, EDX:EAX. This is for compatibility
* with old userspace.
*/
- if (xstate_bv & ~kvm_supported_xcr0())
+ if (xstate_bv & ~kvm_supported_xcr0() ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
load_xsave(vcpu, (u8 *)guest_xsave->region);
} else {
- if (xstate_bv & ~XFEATURE_MASK_FPSSE)
+ if (xstate_bv & ~XFEATURE_MASK_FPSSE ||
+ mxcsr & ~mxcsr_feature_mask)
return -EINVAL;
memcpy(&vcpu->arch.guest_fpu.state.fxsave,
guest_xsave->region, sizeof(struct fxregs_state));
};
case KVM_SET_VAPIC_ADDR: {
struct kvm_vapic_addr va;
+ int idx;
r = -EINVAL;
if (!lapic_in_kernel(vcpu))
r = -EFAULT;
if (copy_from_user(&va, argp, sizeof va))
goto out;
+ idx = srcu_read_lock(&vcpu->kvm->srcu);
r = kvm_lapic_set_vapic_addr(vcpu, va.vapic_addr);
+ srcu_read_unlock(&vcpu->kvm->srcu, idx);
break;
}
case KVM_X86_SETUP_MCE: {
sizeof(struct kvm_pit_config)))
goto out;
create_pit:
- mutex_lock(&kvm->slots_lock);
+ mutex_lock(&kvm->lock);
r = -EEXIST;
if (kvm->arch.vpit)
goto create_pit_unlock;
if (kvm->arch.vpit)
r = 0;
create_pit_unlock:
- mutex_unlock(&kvm->slots_lock);
+ mutex_unlock(&kvm->lock);
break;
case KVM_GET_IRQCHIP: {
/* 0: PIC master, 1: PIC slave, 2: IOAPIC */
mutex_unlock(&kvm->lock);
break;
case KVM_XEN_HVM_CONFIG: {
+ struct kvm_xen_hvm_config xhc;
r = -EFAULT;
- if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
- sizeof(struct kvm_xen_hvm_config)))
+ if (copy_from_user(&xhc, argp, sizeof(xhc)))
goto out;
r = -EINVAL;
- if (kvm->arch.xen_hvm_config.flags)
+ if (xhc.flags)
goto out;
+ memcpy(&kvm->arch.xen_hvm_config, &xhc, sizeof(xhc));
r = 0;
break;
}
num_msrs_to_save = j;
for (i = j = 0; i < ARRAY_SIZE(emulated_msrs); i++) {
- switch (emulated_msrs[i]) {
- case MSR_IA32_SMBASE:
- if (!kvm_x86_ops->cpu_has_high_real_mode_segbase())
- continue;
- break;
- default:
- break;
- }
+ if (!kvm_x86_ops->has_emulated_msr(emulated_msrs[i]))
+ continue;
if (j < i)
emulated_msrs[j] = emulated_msrs[i];
addr, n, v))
&& kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, n, v))
break;
- trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, *(u64 *)v);
+ trace_kvm_mmio(KVM_TRACE_MMIO_READ, n, addr, v);
handled += n;
addr += n;
len -= n;
return X86EMUL_CONTINUE;
}
-int kvm_read_guest_virt(struct x86_emulate_ctxt *ctxt,
+int kvm_read_guest_virt(struct kvm_vcpu *vcpu,
gva_t addr, void *val, unsigned int bytes,
struct x86_exception *exception)
{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
u32 access = (kvm_x86_ops->get_cpl(vcpu) == 3) ? PFERR_USER_MASK : 0;
+ /*
+ * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+ * is returned, but our callers are not ready for that and they blindly
+ * call kvm_inject_page_fault. Ensure that they at least do not leak
+ * uninitialized kernel stack memory into cr2 and error code.
+ */
+ memset(exception, 0, sizeof(*exception));
return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access,
exception);
}
EXPORT_SYMBOL_GPL(kvm_read_guest_virt);
-static int kvm_read_guest_virt_system(struct x86_emulate_ctxt *ctxt,
- gva_t addr, void *val, unsigned int bytes,
- struct x86_exception *exception)
+static int emulator_read_std(struct x86_emulate_ctxt *ctxt,
+ gva_t addr, void *val, unsigned int bytes,
+ struct x86_exception *exception, bool system)
{
struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
- return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, 0, exception);
+ u32 access = 0;
+
+ if (!system && kvm_x86_ops->get_cpl(vcpu) == 3)
+ access |= PFERR_USER_MASK;
+
+ return kvm_read_guest_virt_helper(addr, val, bytes, vcpu, access, exception);
}
static int kvm_read_guest_phys_system(struct x86_emulate_ctxt *ctxt,
return r < 0 ? X86EMUL_IO_NEEDED : X86EMUL_CONTINUE;
}
-int kvm_write_guest_virt_system(struct x86_emulate_ctxt *ctxt,
- gva_t addr, void *val,
- unsigned int bytes,
- struct x86_exception *exception)
+static int kvm_write_guest_virt_helper(gva_t addr, void *val, unsigned int bytes,
+ struct kvm_vcpu *vcpu, u32 access,
+ struct x86_exception *exception)
{
- struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
void *data = val;
int r = X86EMUL_CONTINUE;
while (bytes) {
gpa_t gpa = vcpu->arch.walk_mmu->gva_to_gpa(vcpu, addr,
- PFERR_WRITE_MASK,
+ access,
exception);
unsigned offset = addr & (PAGE_SIZE-1);
unsigned towrite = min(bytes, (unsigned)PAGE_SIZE - offset);
out:
return r;
}
+
+static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *val,
+ unsigned int bytes, struct x86_exception *exception,
+ bool system)
+{
+ struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt);
+ u32 access = PFERR_WRITE_MASK;
+
+ if (!system && kvm_x86_ops->get_cpl(vcpu) == 3)
+ access |= PFERR_USER_MASK;
+
+ /*
+ * FIXME: this should call handle_emulation_failure if X86EMUL_IO_NEEDED
+ * is returned, but our callers are not ready for that and they blindly
+ * call kvm_inject_page_fault. Ensure that they at least do not leak
+ * uninitialized kernel stack memory into cr2 and error code.
+ */
+ memset(exception, 0, sizeof(*exception));
+ return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
+ access, exception);
+}
+
+int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
+ unsigned int bytes, struct x86_exception *exception)
+{
+ return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
+ PFERR_WRITE_MASK, exception);
+}
EXPORT_SYMBOL_GPL(kvm_write_guest_virt_system);
static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
{
if (vcpu->mmio_read_completed) {
trace_kvm_mmio(KVM_TRACE_MMIO_READ, bytes,
- vcpu->mmio_fragments[0].gpa, *(u64 *)val);
+ vcpu->mmio_fragments[0].gpa, val);
vcpu->mmio_read_completed = 0;
return 1;
}
static int write_mmio(struct kvm_vcpu *vcpu, gpa_t gpa, int bytes, void *val)
{
- trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, *(u64 *)val);
+ trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, bytes, gpa, val);
return vcpu_mmio_write(vcpu, gpa, bytes, val);
}
static int read_exit_mmio(struct kvm_vcpu *vcpu, gpa_t gpa,
void *val, int bytes)
{
- trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, 0);
+ trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, bytes, gpa, NULL);
return X86EMUL_IO_NEEDED;
}
static int kernel_pio(struct kvm_vcpu *vcpu, void *pd)
{
- /* TODO: String I/O for in kernel device */
- int r;
+ int r = 0, i;
- if (vcpu->arch.pio.in)
- r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
- vcpu->arch.pio.size, pd);
- else
- r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
- vcpu->arch.pio.port, vcpu->arch.pio.size,
- pd);
+ for (i = 0; i < vcpu->arch.pio.count; i++) {
+ if (vcpu->arch.pio.in)
+ r = kvm_io_bus_read(vcpu, KVM_PIO_BUS, vcpu->arch.pio.port,
+ vcpu->arch.pio.size, pd);
+ else
+ r = kvm_io_bus_write(vcpu, KVM_PIO_BUS,
+ vcpu->arch.pio.port, vcpu->arch.pio.size,
+ pd);
+ if (r)
+ break;
+ pd += vcpu->arch.pio.size;
+ }
return r;
}
if (vcpu->arch.pio.count)
goto data_avail;
+ memset(vcpu->arch.pio_data, 0, size * count);
+
ret = emulator_pio_in_out(vcpu, size, port, val, count, true);
if (ret) {
data_avail:
if (var.unusable) {
memset(desc, 0, sizeof(*desc));
+ if (base3)
+ *base3 = 0;
return false;
}
kvm_x86_ops->set_nmi_mask(emul_to_vcpu(ctxt), masked);
}
+static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
+{
+ return emul_to_vcpu(ctxt)->arch.hflags;
+}
+
+static void emulator_set_hflags(struct x86_emulate_ctxt *ctxt, unsigned emul_flags)
+{
+ kvm_set_hflags(emul_to_vcpu(ctxt), emul_flags);
+}
+
static const struct x86_emulate_ops emulate_ops = {
.read_gpr = emulator_read_gpr,
.write_gpr = emulator_write_gpr,
- .read_std = kvm_read_guest_virt_system,
- .write_std = kvm_write_guest_virt_system,
+ .read_std = emulator_read_std,
+ .write_std = emulator_write_std,
.read_phys = kvm_read_guest_phys_system,
.fetch = kvm_fetch_guest_virt,
.read_emulated = emulator_read_emulated,
.intercept = emulator_intercept,
.get_cpuid = emulator_get_cpuid,
.set_nmi_mask = emulator_set_nmi_mask,
+ .get_hflags = emulator_get_hflags,
+ .set_hflags = emulator_set_hflags,
};
static void toggle_interruptibility(struct kvm_vcpu *vcpu, u32 mask)
kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
ctxt->eflags = kvm_get_rflags(vcpu);
+ ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;
+
ctxt->eip = kvm_rip_read(vcpu);
ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL :
(ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 :
BUILD_BUG_ON(HF_GUEST_MASK != X86EMUL_GUEST_MASK);
BUILD_BUG_ON(HF_SMM_MASK != X86EMUL_SMM_MASK);
BUILD_BUG_ON(HF_SMM_INSIDE_NMI_MASK != X86EMUL_SMM_INSIDE_NMI_MASK);
- ctxt->emul_flags = vcpu->arch.hflags;
init_decode_cache(ctxt);
vcpu->arch.emulate_regs_need_sync_from_vcpu = false;
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
vcpu->run->internal.ndata = 0;
- r = EMULATE_FAIL;
+ r = EMULATE_USER_EXIT;
}
kvm_queue_exception(vcpu, UD_VECTOR);
return dr6;
}
-static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r)
+static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r)
{
struct kvm_run *kvm_run = vcpu->run;
- /*
- * rflags is the old, "raw" value of the flags. The new value has
- * not been saved yet.
- *
- * This is correct even for TF set by the guest, because "the
- * processor will not generate this exception after the instruction
- * that sets the TF flag".
- */
- if (unlikely(rflags & X86_EFLAGS_TF)) {
- if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
- kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 |
- DR6_RTM;
- kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
- kvm_run->debug.arch.exception = DB_VECTOR;
- kvm_run->exit_reason = KVM_EXIT_DEBUG;
- *r = EMULATE_USER_EXIT;
- } else {
- vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
- /*
- * "Certain debug exceptions may clear bit 0-3. The
- * remaining contents of the DR6 register are never
- * cleared by the processor".
- */
- vcpu->arch.dr6 &= ~15;
- vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
- kvm_queue_exception(vcpu, DB_VECTOR);
- }
+ if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+ kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM;
+ kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
+ kvm_run->debug.arch.exception = DB_VECTOR;
+ kvm_run->exit_reason = KVM_EXIT_DEBUG;
+ *r = EMULATE_USER_EXIT;
+ } else {
+ vcpu->arch.emulate_ctxt.eflags &= ~X86_EFLAGS_TF;
+ /*
+ * "Certain debug exceptions may clear bit 0-3. The
+ * remaining contents of the DR6 register are never
+ * cleared by the processor".
+ */
+ vcpu->arch.dr6 &= ~15;
+ vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
+ kvm_queue_exception(vcpu, DB_VECTOR);
}
}
* handle watchpoints yet, those would be handled in
* the emulate_ops.
*/
- if (kvm_vcpu_check_breakpoint(vcpu, &r))
+ if (!(emulation_type & EMULTYPE_SKIP) &&
+ kvm_vcpu_check_breakpoint(vcpu, &r))
return r;
ctxt->interruptibility = 0;
if (reexecute_instruction(vcpu, cr2, write_fault_to_spt,
emulation_type))
return EMULATE_DONE;
+ if (ctxt->have_exception) {
+ /*
+ * #UD should result in just EMULATION_FAILED, and trap-like
+ * exception should not be encountered during decode.
+ */
+ WARN_ON_ONCE(ctxt->exception.vector == UD_VECTOR ||
+ exception_type(ctxt->exception.vector) == EXCPT_TRAP);
+ inject_emulated_exception(vcpu);
+ return EMULATE_DONE;
+ }
if (emulation_type & EMULTYPE_SKIP)
return EMULATE_FAIL;
return handle_emulation_failure(vcpu);
unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
toggle_interruptibility(vcpu, ctxt->interruptibility);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
- if (vcpu->arch.hflags != ctxt->emul_flags)
- kvm_set_hflags(vcpu, ctxt->emul_flags);
- kvm_rip_write(vcpu, ctxt->eip);
- if (r == EMULATE_DONE)
- kvm_vcpu_check_singlestep(vcpu, rflags, &r);
if (!ctxt->have_exception ||
- exception_type(ctxt->exception.vector) == EXCPT_TRAP)
+ exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
+ kvm_rip_write(vcpu, ctxt->eip);
+ if (r == EMULATE_DONE && ctxt->tf)
+ kvm_vcpu_do_singlestep(vcpu, &r);
__kvm_set_rflags(vcpu, ctxt->eflags);
+ }
/*
* For STI, interrupts are shadowed; so KVM_REQ_EVENT will
/* Set the present bit. */
mask |= 1ull;
-#ifdef CONFIG_X86_64
/*
* If reserved bit is not supported, clear the present bit to disable
* mmio page fault.
*/
if (maxphyaddr == 52)
mask &= ~1ull;
-#endif
kvm_mmu_set_mmio_spte_mask(mask);
}
void kvm_arch_exit(void)
{
+ kvm_lapic_exit();
perf_unregister_guest_info_callbacks(&kvm_guest_cbs);
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
kvm_x86_ops->patch_hypercall(vcpu, instruction);
- return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
+ return emulator_write_emulated(ctxt, rip, instruction, 3,
+ &ctxt->exception);
}
static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
kvm_scan_ioapic_routes(vcpu, vcpu->arch.eoi_exit_bitmap);
else {
kvm_x86_ops->sync_pir_to_irr(vcpu);
- kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap);
+ if (ioapic_in_kernel(vcpu->kvm))
+ kvm_ioapic_scan_entry(vcpu, vcpu->arch.eoi_exit_bitmap);
}
kvm_x86_ops->load_eoi_exitmap(vcpu);
}
}
if (kvm_check_request(KVM_REQ_TRIPLE_FAULT, vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+ vcpu->mmio_needed = 0;
r = 0;
goto out;
}
#endif
kvm_rip_write(vcpu, regs->rip);
- kvm_set_rflags(vcpu, regs->rflags);
+ kvm_set_rflags(vcpu, regs->rflags | X86_EFLAGS_FIXED);
vcpu->arch.exception.pending = false;
mp_state->mp_state != KVM_MP_STATE_RUNNABLE)
return -EINVAL;
+ /* INITs are latched while in SMM */
+ if ((is_smm(vcpu) || vcpu->arch.smi_pending) &&
+ (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
+ mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
+ return -EINVAL;
+
if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
vcpu->arch.mp_state = KVM_MP_STATE_INIT_RECEIVED;
set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events);
kvm_update_cpuid(vcpu);
idx = srcu_read_lock(&vcpu->kvm->srcu);
- if (!is_long_mode(vcpu) && is_pae(vcpu)) {
+ if (!is_long_mode(vcpu) && is_pae(vcpu) && is_paging(vcpu)) {
load_pdptrs(vcpu, vcpu->arch.walk_mmu, kvm_read_cr3(vcpu));
mmu_reset_needed = 1;
}
copy_fpregs_to_fpstate(&vcpu->arch.guest_fpu);
__kernel_fpu_end();
++vcpu->stat.fpu_reload;
- /*
- * If using eager FPU mode, or if the guest is a frequent user
- * of the FPU, just leave the FPU active for next time.
- * Every 255 times fpu_counter rolls over to 0; a guest that uses
- * the FPU in bursts will revert to loading it on demand.
- */
- if (!vcpu->arch.eager_fpu) {
- if (++vcpu->fpu_counter < 5)
- kvm_make_request(KVM_REQ_DEACTIVATE_FPU, vcpu);
- }
trace_kvm_fpu(0);
}
void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
{
+ void *wbinvd_dirty_mask = vcpu->arch.wbinvd_dirty_mask;
+
kvmclock_reset(vcpu);
- free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
kvm_x86_ops->vcpu_free(vcpu);
+ free_cpumask_var(wbinvd_dirty_mask);
}
struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
{
int r;
+ vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
kvm_vcpu_mtrr_init(vcpu);
r = vcpu_load(vcpu);
if (r)
kvm_mmu_unload(vcpu);
vcpu_put(vcpu);
- kvm_x86_ops->vcpu_free(vcpu);
+ kvm_arch_vcpu_free(vcpu);
}
void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
slot = id_to_memslot(slots, id);
if (size) {
- if (WARN_ON(slot->npages))
+ if (slot->npages)
return -EEXIST;
/*
sizeof(val));
}
+static int apf_get_user(struct kvm_vcpu *vcpu, u32 *val)
+{
+
+ return kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.apf.data, val,
+ sizeof(u32));
+}
+
void kvm_arch_async_page_not_present(struct kvm_vcpu *vcpu,
struct kvm_async_pf *work)
{
struct kvm_async_pf *work)
{
struct x86_exception fault;
+ u32 val;
- trace_kvm_async_pf_ready(work->arch.token, work->gva);
if (work->wakeup_all)
work->arch.token = ~0; /* broadcast wakeup */
else
kvm_del_async_pf_gfn(vcpu, work->arch.gfn);
+ trace_kvm_async_pf_ready(work->arch.token, work->gva);
- 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);
+ if (vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED &&
+ !apf_get_user(vcpu, &val)) {
+ if (val == KVM_PV_REASON_PAGE_NOT_PRESENT &&
+ vcpu->arch.exception.pending &&
+ vcpu->arch.exception.nr == PF_VECTOR &&
+ !apf_put_user(vcpu, 0)) {
+ vcpu->arch.exception.pending = false;
+ vcpu->arch.exception.nr = 0;
+ vcpu->arch.exception.has_error_code = false;
+ vcpu->arch.exception.error_code = 0;
+ } else if (!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;
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
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);
+ return kvm_can_do_async_pf(vcpu);
}
void kvm_arch_start_assignment(struct kvm *kvm)