summaryrefslogtreecommitdiff
path: root/arch/x86/kvm/x86.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm/x86.c')
-rw-r--r--arch/x86/kvm/x86.c371
1 files changed, 194 insertions, 177 deletions
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ccbd45ecd41a..0e846f0cb83b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -27,7 +27,6 @@
#include "kvm_cache_regs.h"
#include "x86.h"
#include "cpuid.h"
-#include "assigned-dev.h"
#include "pmu.h"
#include "hyperv.h"
@@ -1008,6 +1007,8 @@ static u32 emulated_msrs[] = {
MSR_IA32_MCG_CTL,
MSR_IA32_MCG_EXT_CTL,
MSR_IA32_SMBASE,
+ MSR_PLATFORM_INFO,
+ MSR_MISC_FEATURES_ENABLES,
};
static unsigned num_emulated_msrs;
@@ -1444,10 +1445,10 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
struct kvm *kvm = vcpu->kvm;
u64 offset, ns, elapsed;
unsigned long flags;
- s64 usdiff;
bool matched;
bool already_matched;
u64 data = msr->data;
+ bool synchronizing = false;
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
offset = kvm_compute_tsc_offset(vcpu, data);
@@ -1455,51 +1456,34 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
elapsed = ns - kvm->arch.last_tsc_nsec;
if (vcpu->arch.virtual_tsc_khz) {
- int faulted = 0;
-
- /* n.b - signed multiplication and division required */
- usdiff = data - kvm->arch.last_tsc_write;
-#ifdef CONFIG_X86_64
- usdiff = (usdiff * 1000) / vcpu->arch.virtual_tsc_khz;
-#else
- /* do_div() only does unsigned */
- asm("1: idivl %[divisor]\n"
- "2: xor %%edx, %%edx\n"
- " movl $0, %[faulted]\n"
- "3:\n"
- ".section .fixup,\"ax\"\n"
- "4: movl $1, %[faulted]\n"
- " jmp 3b\n"
- ".previous\n"
-
- _ASM_EXTABLE(1b, 4b)
-
- : "=A"(usdiff), [faulted] "=r" (faulted)
- : "A"(usdiff * 1000), [divisor] "rm"(vcpu->arch.virtual_tsc_khz));
-
-#endif
- do_div(elapsed, 1000);
- usdiff -= elapsed;
- if (usdiff < 0)
- usdiff = -usdiff;
-
- /* idivl overflow => difference is larger than USEC_PER_SEC */
- if (faulted)
- usdiff = USEC_PER_SEC;
- } else
- usdiff = USEC_PER_SEC; /* disable TSC match window below */
+ if (data == 0 && msr->host_initiated) {
+ /*
+ * detection of vcpu initialization -- need to sync
+ * with other vCPUs. This particularly helps to keep
+ * kvm_clock stable after CPU hotplug
+ */
+ synchronizing = true;
+ } else {
+ u64 tsc_exp = kvm->arch.last_tsc_write +
+ nsec_to_cycles(vcpu, elapsed);
+ u64 tsc_hz = vcpu->arch.virtual_tsc_khz * 1000LL;
+ /*
+ * Special case: TSC write with a small delta (1 second)
+ * of virtual cycle time against real time is
+ * interpreted as an attempt to synchronize the CPU.
+ */
+ synchronizing = data < tsc_exp + tsc_hz &&
+ data + tsc_hz > tsc_exp;
+ }
+ }
/*
- * Special case: TSC write with a small delta (1 second) of virtual
- * cycle time against real time is interpreted as an attempt to
- * synchronize the CPU.
- *
* For a reliable TSC, we can match TSC offsets, and for an unstable
* TSC, we add elapsed time in this computation. We could let the
* compensation code attempt to catch up if we fall behind, but
* it's better to try to match offsets from the beginning.
*/
- if (usdiff < USEC_PER_SEC &&
+ if (synchronizing &&
vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
if (!check_tsc_unstable()) {
offset = kvm->arch.cur_tsc_offset;
@@ -1769,16 +1753,17 @@ static void kvm_gen_update_masterclock(struct kvm *kvm)
/* guest entries allowed */
kvm_for_each_vcpu(i, vcpu, kvm)
- clear_bit(KVM_REQ_MCLOCK_INPROGRESS, &vcpu->requests);
+ kvm_clear_request(KVM_REQ_MCLOCK_INPROGRESS, vcpu);
spin_unlock(&ka->pvclock_gtod_sync_lock);
#endif
}
-static u64 __get_kvmclock_ns(struct kvm *kvm)
+u64 get_kvmclock_ns(struct kvm *kvm)
{
struct kvm_arch *ka = &kvm->arch;
struct pvclock_vcpu_time_info hv_clock;
+ u64 ret;
spin_lock(&ka->pvclock_gtod_sync_lock);
if (!ka->use_master_clock) {
@@ -1790,22 +1775,17 @@ static u64 __get_kvmclock_ns(struct kvm *kvm)
hv_clock.system_time = ka->master_kernel_ns + ka->kvmclock_offset;
spin_unlock(&ka->pvclock_gtod_sync_lock);
+ /* both __this_cpu_read() and rdtsc() should be on the same cpu */
+ get_cpu();
+
kvm_get_time_scale(NSEC_PER_SEC, __this_cpu_read(cpu_tsc_khz) * 1000LL,
&hv_clock.tsc_shift,
&hv_clock.tsc_to_system_mul);
- return __pvclock_read_cycles(&hv_clock, rdtsc());
-}
+ ret = __pvclock_read_cycles(&hv_clock, rdtsc());
-u64 get_kvmclock_ns(struct kvm *kvm)
-{
- unsigned long flags;
- s64 ns;
-
- local_irq_save(flags);
- ns = __get_kvmclock_ns(kvm);
- local_irq_restore(flags);
+ put_cpu();
- return ns;
+ return ret;
}
static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
@@ -1813,7 +1793,7 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
struct kvm_vcpu_arch *vcpu = &v->arch;
struct pvclock_vcpu_time_info guest_hv_clock;
- if (unlikely(kvm_vcpu_read_guest_cached(v, &vcpu->pv_time,
+ if (unlikely(kvm_read_guest_cached(v->kvm, &vcpu->pv_time,
&guest_hv_clock, sizeof(guest_hv_clock))))
return;
@@ -1834,9 +1814,9 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
BUILD_BUG_ON(offsetof(struct pvclock_vcpu_time_info, version) != 0);
vcpu->hv_clock.version = guest_hv_clock.version + 1;
- kvm_vcpu_write_guest_cached(v, &vcpu->pv_time,
- &vcpu->hv_clock,
- sizeof(vcpu->hv_clock.version));
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
smp_wmb();
@@ -1850,16 +1830,16 @@ static void kvm_setup_pvclock_page(struct kvm_vcpu *v)
trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
- kvm_vcpu_write_guest_cached(v, &vcpu->pv_time,
- &vcpu->hv_clock,
- sizeof(vcpu->hv_clock));
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock));
smp_wmb();
vcpu->hv_clock.version++;
- kvm_vcpu_write_guest_cached(v, &vcpu->pv_time,
- &vcpu->hv_clock,
- sizeof(vcpu->hv_clock.version));
+ kvm_write_guest_cached(v->kvm, &vcpu->pv_time,
+ &vcpu->hv_clock,
+ sizeof(vcpu->hv_clock.version));
}
static int kvm_guest_time_update(struct kvm_vcpu *v)
@@ -2092,7 +2072,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
return 0;
}
- if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.apf.data, gpa,
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
sizeof(u32)))
return 1;
@@ -2111,7 +2091,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
return;
- if (unlikely(kvm_vcpu_read_guest_cached(vcpu, &vcpu->arch.st.stime,
+ if (unlikely(kvm_read_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
return;
@@ -2122,7 +2102,7 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
vcpu->arch.st.steal.version += 1;
- kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime,
+ kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
smp_wmb();
@@ -2131,14 +2111,14 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
vcpu->arch.st.last_steal;
vcpu->arch.st.last_steal = current->sched_info.run_delay;
- kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime,
+ kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
smp_wmb();
vcpu->arch.st.steal.version += 1;
- kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.st.stime,
+ kvm_write_guest_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal, sizeof(struct kvm_steal_time));
}
@@ -2155,6 +2135,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_VM_HSAVE_PA:
case MSR_AMD64_PATCH_LOADER:
case MSR_AMD64_BU_CFG2:
+ case MSR_AMD64_DC_CFG:
break;
case MSR_EFER:
@@ -2230,8 +2211,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
bool tmp = (msr == MSR_KVM_SYSTEM_TIME);
if (ka->boot_vcpu_runs_old_kvmclock != tmp)
- set_bit(KVM_REQ_MASTERCLOCK_UPDATE,
- &vcpu->requests);
+ kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
ka->boot_vcpu_runs_old_kvmclock = tmp;
}
@@ -2243,7 +2223,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (!(data & 1))
break;
- if (kvm_vcpu_gfn_to_hva_cache_init(vcpu,
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
&vcpu->arch.pv_time, data & ~1ULL,
sizeof(struct pvclock_vcpu_time_info)))
vcpu->arch.pv_time_enabled = false;
@@ -2264,7 +2244,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (data & KVM_STEAL_RESERVED_MASK)
return 1;
- if (kvm_vcpu_gfn_to_hva_cache_init(vcpu, &vcpu->arch.st.stime,
+ if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
data & KVM_STEAL_VALID_BITS,
sizeof(struct kvm_steal_time)))
return 1;
@@ -2331,6 +2311,21 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
vcpu->arch.osvw.status = data;
break;
+ case MSR_PLATFORM_INFO:
+ if (!msr_info->host_initiated ||
+ data & ~MSR_PLATFORM_INFO_CPUID_FAULT ||
+ (!(data & MSR_PLATFORM_INFO_CPUID_FAULT) &&
+ cpuid_fault_enabled(vcpu)))
+ return 1;
+ vcpu->arch.msr_platform_info = data;
+ break;
+ case MSR_MISC_FEATURES_ENABLES:
+ if (data & ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT ||
+ (data & MSR_MISC_FEATURES_ENABLES_CPUID_FAULT &&
+ !supports_cpuid_fault(vcpu)))
+ return 1;
+ vcpu->arch.msr_misc_features_enables = data;
+ break;
default:
if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
return xen_hvm_config(vcpu, data);
@@ -2417,6 +2412,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_FAM10H_MMIO_CONF_BASE:
case MSR_AMD64_BU_CFG2:
case MSR_IA32_PERF_CTL:
+ case MSR_AMD64_DC_CFG:
msr_info->data = 0;
break;
case MSR_K7_EVNTSEL0 ... MSR_K7_EVNTSEL3:
@@ -2545,6 +2541,12 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
msr_info->data = vcpu->arch.osvw.status;
break;
+ case MSR_PLATFORM_INFO:
+ msr_info->data = vcpu->arch.msr_platform_info;
+ break;
+ case MSR_MISC_FEATURES_ENABLES:
+ msr_info->data = vcpu->arch.msr_misc_features_enables;
+ break;
default:
if (kvm_pmu_is_valid_msr(vcpu, msr_info->index))
return kvm_pmu_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -2675,15 +2677,14 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_SET_BOOT_CPU_ID:
case KVM_CAP_SPLIT_IRQCHIP:
case KVM_CAP_IMMEDIATE_EXIT:
-#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
- case KVM_CAP_ASSIGN_DEV_IRQ:
- case KVM_CAP_PCI_2_3:
-#endif
r = 1;
break;
case KVM_CAP_ADJUST_CLOCK:
r = KVM_CLOCK_TSC_STABLE;
break;
+ case KVM_CAP_X86_GUEST_MWAIT:
+ r = kvm_mwait_in_guest();
+ break;
case KVM_CAP_X86_SMM:
/* SMBASE is usually relocated above 1M on modern chipsets,
* and SMM handlers might indeed rely on 4G segment limits,
@@ -2695,9 +2696,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
*/
r = kvm_x86_ops->cpu_has_high_real_mode_segbase();
break;
- case KVM_CAP_COALESCED_MMIO:
- r = KVM_COALESCED_MMIO_PAGE_OFFSET;
- break;
case KVM_CAP_VAPIC:
r = !kvm_x86_ops->cpu_has_accelerated_tpr();
break;
@@ -2713,11 +2711,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_PV_MMU: /* obsolete */
r = 0;
break;
-#ifdef CONFIG_KVM_DEVICE_ASSIGNMENT
- case KVM_CAP_IOMMU:
- r = iommu_present(&pci_bus_type);
- break;
-#endif
case KVM_CAP_MCE:
r = KVM_MAX_MCE_BANKS;
break;
@@ -2816,11 +2809,6 @@ static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
return kvm_arch_has_noncoherent_dma(vcpu->kvm);
}
-static inline void kvm_migrate_timers(struct kvm_vcpu *vcpu)
-{
- set_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests);
-}
-
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
/* Address WBINVD may be executed by guest */
@@ -2864,7 +2852,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (!vcpu->kvm->arch.use_master_clock || vcpu->cpu == -1)
kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
if (vcpu->cpu != cpu)
- kvm_migrate_timers(vcpu);
+ kvm_make_request(KVM_REQ_MIGRATE_TIMER, vcpu);
vcpu->cpu = cpu;
}
@@ -2878,7 +2866,7 @@ static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
vcpu->arch.st.steal.preempted = 1;
- kvm_vcpu_write_guest_offset_cached(vcpu, &vcpu->arch.st.stime,
+ kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
&vcpu->arch.st.steal.preempted,
offsetof(struct kvm_steal_time, preempted),
sizeof(vcpu->arch.st.steal.preempted));
@@ -3124,7 +3112,14 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
return -EINVAL;
if (events->exception.injected &&
- (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
+ (events->exception.nr > 31 || events->exception.nr == NMI_VECTOR ||
+ is_guest_mode(vcpu)))
+ 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);
@@ -3301,11 +3296,14 @@ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
}
}
+#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 (boot_cpu_has(X86_FEATURE_XSAVE)) {
/*
@@ -3313,11 +3311,13 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
* 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));
@@ -3721,22 +3721,21 @@ static int kvm_vm_ioctl_get_nr_mmu_pages(struct kvm *kvm)
static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
+ struct kvm_pic *pic = kvm->arch.vpic;
int r;
r = 0;
switch (chip->chip_id) {
case KVM_IRQCHIP_PIC_MASTER:
- memcpy(&chip->chip.pic,
- &pic_irqchip(kvm)->pics[0],
+ memcpy(&chip->chip.pic, &pic->pics[0],
sizeof(struct kvm_pic_state));
break;
case KVM_IRQCHIP_PIC_SLAVE:
- memcpy(&chip->chip.pic,
- &pic_irqchip(kvm)->pics[1],
+ memcpy(&chip->chip.pic, &pic->pics[1],
sizeof(struct kvm_pic_state));
break;
case KVM_IRQCHIP_IOAPIC:
- r = kvm_get_ioapic(kvm, &chip->chip.ioapic);
+ kvm_get_ioapic(kvm, &chip->chip.ioapic);
break;
default:
r = -EINVAL;
@@ -3747,32 +3746,31 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
{
+ struct kvm_pic *pic = kvm->arch.vpic;
int r;
r = 0;
switch (chip->chip_id) {
case KVM_IRQCHIP_PIC_MASTER:
- spin_lock(&pic_irqchip(kvm)->lock);
- memcpy(&pic_irqchip(kvm)->pics[0],
- &chip->chip.pic,
+ spin_lock(&pic->lock);
+ memcpy(&pic->pics[0], &chip->chip.pic,
sizeof(struct kvm_pic_state));
- spin_unlock(&pic_irqchip(kvm)->lock);
+ spin_unlock(&pic->lock);
break;
case KVM_IRQCHIP_PIC_SLAVE:
- spin_lock(&pic_irqchip(kvm)->lock);
- memcpy(&pic_irqchip(kvm)->pics[1],
- &chip->chip.pic,
+ spin_lock(&pic->lock);
+ memcpy(&pic->pics[1], &chip->chip.pic,
sizeof(struct kvm_pic_state));
- spin_unlock(&pic_irqchip(kvm)->lock);
+ spin_unlock(&pic->lock);
break;
case KVM_IRQCHIP_IOAPIC:
- r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
+ kvm_set_ioapic(kvm, &chip->chip.ioapic);
break;
default:
r = -EINVAL;
break;
}
- kvm_pic_update_irq(pic_irqchip(kvm));
+ kvm_pic_update_irq(pic);
return r;
}
@@ -4018,20 +4016,14 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = kvm_ioapic_init(kvm);
if (r) {
- mutex_lock(&kvm->slots_lock);
kvm_pic_destroy(kvm);
- mutex_unlock(&kvm->slots_lock);
goto create_irqchip_unlock;
}
r = kvm_setup_default_irq_routing(kvm);
if (r) {
- mutex_lock(&kvm->slots_lock);
- mutex_lock(&kvm->irq_lock);
kvm_ioapic_destroy(kvm);
kvm_pic_destroy(kvm);
- mutex_unlock(&kvm->irq_lock);
- mutex_unlock(&kvm->slots_lock);
goto create_irqchip_unlock;
}
/* Write kvm->irq_routing before enabling irqchip_in_kernel. */
@@ -4196,10 +4188,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
goto out;
r = 0;
- local_irq_disable();
- now_ns = __get_kvmclock_ns(kvm);
+ now_ns = get_kvmclock_ns(kvm);
kvm->arch.kvmclock_offset += user_ns.clock - now_ns;
- local_irq_enable();
kvm_gen_update_masterclock(kvm);
break;
}
@@ -4207,11 +4197,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
struct kvm_clock_data user_ns;
u64 now_ns;
- local_irq_disable();
- now_ns = __get_kvmclock_ns(kvm);
+ now_ns = get_kvmclock_ns(kvm);
user_ns.clock = now_ns;
user_ns.flags = kvm->arch.use_master_clock ? KVM_CLOCK_TSC_STABLE : 0;
- local_irq_enable();
memset(&user_ns.pad, 0, sizeof(user_ns.pad));
r = -EFAULT;
@@ -4230,7 +4218,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
break;
}
default:
- r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg);
+ r = -ENOTTY;
}
out:
return r;
@@ -4843,16 +4831,20 @@ emul_write:
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;
}
@@ -4890,6 +4882,8 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt,
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:
@@ -5073,6 +5067,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
if (var.unusable) {
memset(desc, 0, sizeof(*desc));
+ if (base3)
+ *base3 = 0;
return false;
}
@@ -5223,6 +5219,16 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked)
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,
@@ -5262,6 +5268,8 @@ static const struct x86_emulate_ops emulate_ops = {
.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)
@@ -5305,6 +5313,8 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
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 :
@@ -5314,7 +5324,6 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
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;
@@ -5521,36 +5530,25 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
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 {
- /*
- * "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 {
+ /*
+ * "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);
}
}
@@ -5560,7 +5558,17 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
int r = EMULATE_DONE;
kvm_x86_ops->skip_emulated_instruction(vcpu);
- kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+
+ /*
+ * 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))
+ kvm_vcpu_do_singlestep(vcpu, &r);
return r == EMULATE_DONE;
}
EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction);
@@ -5718,11 +5726,10 @@ restart:
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 (r == EMULATE_DONE &&
+ (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+ kvm_vcpu_do_singlestep(vcpu, &r);
if (!ctxt->have_exception ||
exception_type(ctxt->exception.vector) == EXCPT_TRAP)
__kvm_set_rflags(vcpu, ctxt->eflags);
@@ -6869,7 +6876,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
/*
* 1) We should set ->mode before checking ->requests. Please see
- * the comment in kvm_make_all_cpus_request.
+ * the comment in kvm_vcpu_exiting_guest_mode().
*
* 2) For APICv, we should set ->mode before checking PIR.ON. This
* pairs with the memory barrier implicit in pi_test_and_set_on
@@ -7051,7 +7058,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
if (r <= 0)
break;
- clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
+ kvm_clear_request(KVM_REQ_PENDING_TIMER, vcpu);
if (kvm_cpu_has_pending_timer(vcpu))
kvm_inject_pending_timer_irqs(vcpu);
@@ -7179,7 +7186,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
if (unlikely(vcpu->arch.mp_state == KVM_MP_STATE_UNINITIALIZED)) {
kvm_vcpu_block(vcpu);
kvm_apic_accept_events(vcpu);
- clear_bit(KVM_REQ_UNHALT, &vcpu->requests);
+ kvm_clear_request(KVM_REQ_UNHALT, vcpu);
r = -EAGAIN;
goto out;
}
@@ -7355,6 +7362,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
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);
@@ -7724,6 +7737,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
if (!init_event) {
kvm_pmu_reset(vcpu);
vcpu->arch.smbase = 0x30000;
+
+ vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
+ vcpu->arch.msr_misc_features_enables = 0;
}
memset(vcpu->arch.regs, 0, sizeof(vcpu->arch.regs));
@@ -8068,7 +8084,6 @@ void kvm_arch_sync_events(struct kvm *kvm)
{
cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
- kvm_free_all_assigned_devices(kvm);
kvm_free_pit(kvm);
}
@@ -8152,7 +8167,6 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
}
if (kvm_x86_ops->vm_destroy)
kvm_x86_ops->vm_destroy(kvm);
- kvm_iommu_unmap_guest(kvm);
kvm_pic_destroy(kvm);
kvm_ioapic_destroy(kvm);
kvm_free_vcpus(kvm);
@@ -8199,13 +8213,13 @@ int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
slot->base_gfn, level) + 1;
slot->arch.rmap[i] =
- kvm_kvzalloc(lpages * sizeof(*slot->arch.rmap[i]));
+ kvzalloc(lpages * sizeof(*slot->arch.rmap[i]), GFP_KERNEL);
if (!slot->arch.rmap[i])
goto out_free;
if (i == 0)
continue;
- linfo = kvm_kvzalloc(lpages * sizeof(*linfo));
+ linfo = kvzalloc(lpages * sizeof(*linfo), GFP_KERNEL);
if (!linfo)
goto out_free;
@@ -8382,10 +8396,13 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
if (vcpu->arch.pv.pv_unhalted)
return true;
- if (atomic_read(&vcpu->arch.nmi_queued))
+ if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+ (vcpu->arch.nmi_pending &&
+ kvm_x86_ops->nmi_allowed(vcpu)))
return true;
- if (test_bit(KVM_REQ_SMI, &vcpu->requests))
+ if (kvm_test_request(KVM_REQ_SMI, vcpu) ||
+ (vcpu->arch.smi_pending && !is_smm(vcpu)))
return true;
if (kvm_arch_interrupt_allowed(vcpu) &&
@@ -8536,8 +8553,9 @@ static void kvm_del_async_pf_gfn(struct kvm_vcpu *vcpu, gfn_t gfn)
static int apf_put_user(struct kvm_vcpu *vcpu, u32 val)
{
- return kvm_vcpu_write_guest_cached(vcpu, &vcpu->arch.apf.data, &val,
- sizeof(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,
@@ -8591,8 +8609,7 @@ 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);
+ return kvm_can_do_async_pf(vcpu);
}
void kvm_arch_start_assignment(struct kvm *kvm)
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-20 23:15:48 +0300