__u8 pad2[30];
};
- If the KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag is returned from the
- KVM_CAP_XEN_HVM check, it may be set in the flags field of this ioctl.
- This requests KVM to generate the contents of the hypercall page
- automatically; hypercalls will be intercepted and passed to userspace
- through KVM_EXIT_XEN. In this case, all of the blob size and address
- fields must be zero.
+ If certain flags are returned from the KVM_CAP_XEN_HVM check, they may
+ be set in the flags field of this ioctl:
+
+ The KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL flag requests KVM to generate
+ the contents of the hypercall page automatically; hypercalls will be
+ intercepted and passed to userspace through KVM_EXIT_XEN. In this
+ ase, all of the blob size and address fields must be zero.
+
+ The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates to KVM that userspace
+ will always use the KVM_XEN_HVM_EVTCHN_SEND ioctl to deliver event
+ channel interrupts rather than manipulating the guest's shared_info
+ structures directly. This, in turn, may allow KVM to enable features
+ such as intercepting the SCHEDOP_poll hypercall to accelerate PV
+ spinlock operation for the guest. Userspace may still use the ioctl
+ to deliver events if it was advertised, even if userspace does not
+ send this indication that it will always do so
No other flags are currently valid in the struct kvm_xen_hvm_config.
4.55 KVM_SET_TSC_KHZ
--------------------
- :Capability: KVM_CAP_TSC_CONTROL
+ :Capability: KVM_CAP_TSC_CONTROL / KVM_CAP_VM_TSC_CONTROL
:Architectures: x86
- :Type: vcpu ioctl
+ :Type: vcpu ioctl / vm ioctl
:Parameters: virtual tsc_khz
:Returns: 0 on success, -1 on error
Specifies the tsc frequency for the virtual machine. The unit of the
frequency is KHz.
+ If the KVM_CAP_VM_TSC_CONTROL capability is advertised, this can also
+ be used as a vm ioctl to set the initial tsc frequency of subsequently
+ created vCPUs.
4.56 KVM_GET_TSC_KHZ
--------------------
- :Capability: KVM_CAP_GET_TSC_KHZ
+ :Capability: KVM_CAP_GET_TSC_KHZ / KVM_CAP_VM_TSC_CONTROL
:Architectures: x86
- :Type: vcpu ioctl
+ :Type: vcpu ioctl / vm ioctl
:Parameters: none
:Returns: virtual tsc-khz on success, negative value on error
struct {
__u64 gfn;
} shared_info;
- __u64 pad[4];
+ struct {
+ __u32 send_port;
+ __u32 type; /* EVTCHNSTAT_ipi / EVTCHNSTAT_interdomain */
+ __u32 flags;
+ union {
+ struct {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+ } port;
+ struct {
+ __u32 port; /* Zero for eventfd */
+ __s32 fd;
+ } eventfd;
+ __u32 padding[4];
+ } deliver;
+ } evtchn;
+ __u32 xen_version;
+ __u64 pad[8];
} u;
};
KVM_XEN_ATTR_TYPE_UPCALL_VECTOR
Sets the exception vector used to deliver Xen event channel upcalls.
+ This is the HVM-wide vector injected directly by the hypervisor
+ (not through the local APIC), typically configured by a guest via
+ HVM_PARAM_CALLBACK_IRQ.
+
+ KVM_XEN_ATTR_TYPE_EVTCHN
+ This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+ support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures
+ an outbound port number for interception of EVTCHNOP_send requests
+ from the guest. A given sending port number may be directed back
+ to a specified vCPU (by APIC ID) / port / priority on the guest,
+ or to trigger events on an eventfd. The vCPU and priority can be
+ changed by setting KVM_XEN_EVTCHN_UPDATE in a subsequent call,
+ but other fields cannot change for a given sending port. A port
+ mapping is removed by using KVM_XEN_EVTCHN_DEASSIGN in the flags
+ field.
+
+ KVM_XEN_ATTR_TYPE_XEN_VERSION
+ This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+ support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It configures
+ the 32-bit version code returned to the guest when it invokes the
+ XENVER_version call; typically (XEN_MAJOR << 16 | XEN_MINOR). PV
+ Xen guests will often use this to as a dummy hypercall to trigger
+ event channel delivery, so responding within the kernel without
+ exiting to userspace is beneficial.
4.127 KVM_XEN_HVM_GET_ATTR
--------------------------
:Returns: 0 on success, < 0 on error
Allows Xen VM attributes to be read. For the structure and types,
- see KVM_XEN_HVM_SET_ATTR above.
+ see KVM_XEN_HVM_SET_ATTR above. The KVM_XEN_ATTR_TYPE_EVTCHN
+ attribute cannot be read.
4.128 KVM_XEN_VCPU_SET_ATTR
---------------------------
__u64 time_blocked;
__u64 time_offline;
} runstate;
+ __u32 vcpu_id;
+ struct {
+ __u32 port;
+ __u32 priority;
+ __u64 expires_ns;
+ } timer;
+ __u8 vector;
} u;
};
or RUNSTATE_offline) to set the current accounted state as of the
adjusted state_entry_time.
+ KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID
+ This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+ support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the Xen
+ vCPU ID of the given vCPU, to allow timer-related VCPU operations to
+ be intercepted by KVM.
+
+ KVM_XEN_VCPU_ATTR_TYPE_TIMER
+ This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+ support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the
+ event channel port/priority for the VIRQ_TIMER of the vCPU, as well
+ as allowing a pending timer to be saved/restored.
+
+ KVM_XEN_VCPU_ATTR_TYPE_UPCALL_VECTOR
+ This attribute is available when the KVM_CAP_XEN_HVM ioctl indicates
+ support for KVM_XEN_HVM_CONFIG_EVTCHN_SEND features. It sets the
+ per-vCPU local APIC upcall vector, configured by a Xen guest with
+ the HVMOP_set_evtchn_upcall_vector hypercall. This is typically
+ used by Windows guests, and is distinct from the HVM-wide upcall
+ vector configured with HVM_PARAM_CALLBACK_IRQ.
+
+
4.129 KVM_XEN_VCPU_GET_ATTR
---------------------------
The offsets of the state save areas in struct kvm_xsave follow the contents
of CPUID leaf 0xD on the host.
+ 4.135 KVM_XEN_HVM_EVTCHN_SEND
+ -----------------------------
+
+ :Capability: KVM_CAP_XEN_HVM / KVM_XEN_HVM_CONFIG_EVTCHN_SEND
+ :Architectures: x86
+ :Type: vm ioctl
+ :Parameters: struct kvm_irq_routing_xen_evtchn
+ :Returns: 0 on success, < 0 on error
+
+
+ ::
+
+ struct kvm_irq_routing_xen_evtchn {
+ __u32 port;
+ __u32 vcpu;
+ __u32 priority;
+ };
+
+ This ioctl injects an event channel interrupt directly to the guest vCPU.
5. The kvm_run structure
========================
unsigned long args[6];
unsigned long ret[2];
} riscv_sbi;
+
If exit reason is KVM_EXIT_RISCV_SBI then it indicates that the VCPU has
done a SBI call which is not handled by KVM RISC-V kernel module. The details
of the SBI call are available in 'riscv_sbi' member of kvm_run structure. The
Additionally, when this quirk is disabled,
KVM clears CPUID.01H:ECX[bit 3] if
IA32_MISC_ENABLE[bit 18] is cleared.
+
+ KVM_X86_QUIRK_FIX_HYPERCALL_INSN By default, KVM rewrites guest
+ VMMCALL/VMCALL instructions to match the
+ vendor's hypercall instruction for the
+ system. When this quirk is disabled, KVM
+ will no longer rewrite invalid guest
+ hypercall instructions. Executing the
+ incorrect hypercall instruction will
+ generate a #UD within the guest.
=================================== ============================================
8. Other capabilities.
#define KVM_XEN_HVM_CONFIG_HYPERCALL_MSR (1 << 0)
#define KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL (1 << 1)
#define KVM_XEN_HVM_CONFIG_SHARED_INFO (1 << 2)
- #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 2)
- #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 3)
+ #define KVM_XEN_HVM_CONFIG_RUNSTATE (1 << 3)
+ #define KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL (1 << 4)
+ #define KVM_XEN_HVM_CONFIG_EVTCHN_SEND (1 << 5)
The KVM_XEN_HVM_CONFIG_HYPERCALL_MSR flag indicates that the KVM_XEN_HVM_CONFIG
ioctl is available, for the guest to set its hypercall page.
of the type KVM_IRQ_ROUTING_XEN_EVTCHN are supported, with the priority
field set to indicate 2 level event channel delivery.
+ The KVM_XEN_HVM_CONFIG_EVTCHN_SEND flag indicates that KVM supports
+ injecting event channel events directly into the guest with the
+ KVM_XEN_HVM_EVTCHN_SEND ioctl. It also indicates support for the
+ KVM_XEN_ATTR_TYPE_EVTCHN/XEN_VERSION HVM attributes and the
+ KVM_XEN_VCPU_ATTR_TYPE_VCPU_ID/TIMER/UPCALL_VECTOR vCPU attributes.
+ related to event channel delivery, timers, and the XENVER_version
+ interception.
+
8.31 KVM_CAP_PPC_MULTITCE
-------------------------
bool intr;
};
+#define KVM_PMC_MAX_FIXED 3
struct kvm_pmu {
unsigned nr_arch_gp_counters;
unsigned nr_arch_fixed_counters;
u64 raw_event_mask;
u8 version;
struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
- struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
+ struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
struct irq_work irq_work;
DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
struct kvm_vcpu_xen {
u64 hypercall_rip;
u32 current_runstate;
- bool vcpu_info_set;
- bool vcpu_time_info_set;
- bool runstate_set;
- struct gfn_to_hva_cache vcpu_info_cache;
- struct gfn_to_hva_cache vcpu_time_info_cache;
- struct gfn_to_hva_cache runstate_cache;
+ u8 upcall_vector;
+ struct gfn_to_pfn_cache vcpu_info_cache;
+ struct gfn_to_pfn_cache vcpu_time_info_cache;
+ struct gfn_to_pfn_cache runstate_cache;
u64 last_steal;
u64 runstate_entry_time;
u64 runstate_times[4];
unsigned long evtchn_pending_sel;
+ u32 vcpu_id; /* The Xen / ACPI vCPU ID */
+ u32 timer_virq;
+ u64 timer_expires; /* In guest epoch */
+ atomic_t timer_pending;
+ struct hrtimer timer;
+ int poll_evtchn;
+ struct timer_list poll_timer;
};
struct kvm_vcpu_arch {
gpa_t time;
struct pvclock_vcpu_time_info hv_clock;
unsigned int hw_tsc_khz;
- struct gfn_to_hva_cache pv_time;
- bool pv_time_enabled;
+ struct gfn_to_pfn_cache pv_time;
/* set guest stopped flag in pvclock flags field */
bool pvclock_set_guest_stopped_request;
HV_TSC_PAGE_UNSET = 0,
/* TSC page MSR was written by the guest, update pending */
HV_TSC_PAGE_GUEST_CHANGED,
- /* TSC page MSR was written by KVM userspace, update pending */
+ /* TSC page update was triggered from the host side */
HV_TSC_PAGE_HOST_CHANGED,
/* TSC page was properly set up and is currently active */
HV_TSC_PAGE_SET,
- /* TSC page is currently being updated and therefore is inactive */
- HV_TSC_PAGE_UPDATING,
/* TSC page was set up with an inaccessible GPA */
HV_TSC_PAGE_BROKEN,
};
/* Xen emulation context */
struct kvm_xen {
+ u32 xen_version;
bool long_mode;
u8 upcall_vector;
struct gfn_to_pfn_cache shinfo_cache;
+ struct idr evtchn_ports;
+ unsigned long poll_mask[BITS_TO_LONGS(KVM_MAX_VCPUS)];
};
enum kvm_irqchip_mode {
APICV_INHIBIT_REASON_X2APIC,
APICV_INHIBIT_REASON_BLOCKIRQ,
APICV_INHIBIT_REASON_ABSENT,
+ APICV_INHIBIT_REASON_SEV,
};
struct kvm_arch {
u64 cur_tsc_generation;
int nr_vcpus_matched_tsc;
+ u32 default_tsc_khz;
+
seqcount_raw_spinlock_t pvclock_sc;
bool use_master_clock;
u64 master_kernel_ns;
int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
+
+ /*
+ * Returns vCPU specific APICv inhibit reasons
+ */
+ unsigned long (*vcpu_get_apicv_inhibit_reasons)(struct kvm_vcpu *vcpu);
};
struct kvm_x86_nested_ops {
#define kvm_arch_pmi_in_guest(vcpu) \
((vcpu) && (vcpu)->arch.handling_intr_from_guest)
-int kvm_mmu_module_init(void);
-void kvm_mmu_module_exit(void);
+void kvm_mmu_x86_module_init(void);
+int kvm_mmu_vendor_module_init(void);
+void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
struct x86_exception *exception);
bool kvm_apicv_activated(struct kvm *kvm);
+ bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu);
void kvm_vcpu_update_apicv(struct kvm_vcpu *vcpu);
void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
enum kvm_apicv_inhibit reason, bool set);
KVM_X86_QUIRK_CD_NW_CLEARED | \
KVM_X86_QUIRK_LAPIC_MMIO_HOLE | \
KVM_X86_QUIRK_OUT_7E_INC_RIP | \
- KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)
+ KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT | \
+ KVM_X86_QUIRK_FIX_HYPERCALL_INSN)
#endif /* _ASM_X86_KVM_HOST_H */
}
#endif
-"ret;"
+ #if defined(CONFIG_X86_32) || !defined(CONFIG_SMP)
+ bool __kvm_vcpu_is_preempted(long cpu);
+
+ __visible bool __kvm_vcpu_is_preempted(long cpu)
+ {
+ struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
+
+ return !!(src->preempted & KVM_VCPU_PREEMPTED);
+ }
+ PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
+
+ #else
+
+ #include <asm/asm-offsets.h>
+
+ extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
+
+ /*
+ * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
+ * restoring to/from the stack.
+ */
+ asm(
+ ".pushsection .text;"
+ ".global __raw_callee_save___kvm_vcpu_is_preempted;"
+ ".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
+ "__raw_callee_save___kvm_vcpu_is_preempted:"
++ASM_ENDBR
+ "movq __per_cpu_offset(,%rdi,8), %rax;"
+ "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
+ "setne %al;"
++ASM_RET
+ ".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
+ ".popsection");
+
+ #endif
+
static void __init kvm_guest_init(void)
{
int i;
if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
has_steal_clock = 1;
static_call_update(pv_steal_clock, kvm_steal_clock);
+
+ pv_ops.lock.vcpu_is_preempted =
+ PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
}
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
}
}
- #ifdef CONFIG_X86_32
- __visible bool __kvm_vcpu_is_preempted(long cpu)
- {
- struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
-
- return !!(src->preempted & KVM_VCPU_PREEMPTED);
- }
- PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
-
- #else
-
- #include <asm/asm-offsets.h>
-
- extern bool __raw_callee_save___kvm_vcpu_is_preempted(long);
-
- /*
- * Hand-optimize version for x86-64 to avoid 8 64-bit register saving and
- * restoring to/from the stack.
- */
- asm(
- ".pushsection .text;"
- ".global __raw_callee_save___kvm_vcpu_is_preempted;"
- ".type __raw_callee_save___kvm_vcpu_is_preempted, @function;"
- "__raw_callee_save___kvm_vcpu_is_preempted:"
- ASM_ENDBR
- "movq __per_cpu_offset(,%rdi,8), %rax;"
- "cmpb $0, " __stringify(KVM_STEAL_TIME_preempted) "+steal_time(%rax);"
- "setne %al;"
- ASM_RET
- ".size __raw_callee_save___kvm_vcpu_is_preempted, .-__raw_callee_save___kvm_vcpu_is_preempted;"
- ".popsection");
-
- #endif
-
/*
* Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
*/
pv_ops.lock.wait = kvm_wait;
pv_ops.lock.kick = kvm_kick_cpu;
- if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
- pv_ops.lock.vcpu_is_preempted =
- PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
- }
/*
* When PV spinlock is enabled which is preferred over
* virt_spin_lock(), virt_spin_lock_key's value is meaningless.
&(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \
if ((_sp)->gfn != (_gfn) || (_sp)->role.direct) {} else
- static bool kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
+ static int kvm_sync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
struct list_head *invalid_list)
{
int ret = vcpu->arch.mmu->sync_page(vcpu, sp);
- if (ret < 0) {
+ if (ret < 0)
kvm_mmu_prepare_zap_page(vcpu->kvm, sp, invalid_list);
- return false;
- }
-
- return !!ret;
+ return ret;
}
static bool kvm_mmu_remote_flush_or_zap(struct kvm *kvm,
for_each_sp(pages, sp, parents, i) {
kvm_unlink_unsync_page(vcpu->kvm, sp);
- flush |= kvm_sync_page(vcpu, sp, &invalid_list);
+ flush |= kvm_sync_page(vcpu, sp, &invalid_list) > 0;
mmu_pages_clear_parents(&parents);
}
if (need_resched() || rwlock_needbreak(&vcpu->kvm->mmu_lock)) {
struct hlist_head *sp_list;
unsigned quadrant;
struct kvm_mmu_page *sp;
+ int ret;
int collisions = 0;
LIST_HEAD(invalid_list);
* If the sync fails, the page is zapped. If so, break
* in order to rebuild it.
*/
- if (!kvm_sync_page(vcpu, sp, &invalid_list))
+ ret = kvm_sync_page(vcpu, sp, &invalid_list);
+ if (ret < 0)
break;
WARN_ON(!list_empty(&invalid_list));
- kvm_flush_remote_tlbs(vcpu->kvm);
+ if (ret > 0)
+ kvm_flush_remote_tlbs(vcpu->kvm);
}
__clear_sp_write_flooding_count(sp);
return 0;
}
-int kvm_mmu_module_init(void)
+/*
+ * nx_huge_pages needs to be resolved to true/false when kvm.ko is loaded, as
+ * its default value of -1 is technically undefined behavior for a boolean.
+ */
+void kvm_mmu_x86_module_init(void)
{
- int ret = -ENOMEM;
-
if (nx_huge_pages == -1)
__set_nx_huge_pages(get_nx_auto_mode());
+}
+
+/*
+ * The bulk of the MMU initialization is deferred until the vendor module is
+ * loaded as many of the masks/values may be modified by VMX or SVM, i.e. need
+ * to be reset when a potentially different vendor module is loaded.
+ */
+int kvm_mmu_vendor_module_init(void)
+{
+ int ret = -ENOMEM;
/*
* MMU roles use union aliasing which is, generally speaking, an
mmu_free_memory_caches(vcpu);
}
-void kvm_mmu_module_exit(void)
+void kvm_mmu_vendor_module_exit(void)
{
mmu_destroy_caches();
percpu_counter_destroy(&kvm_total_used_mmu_pages);
return err;
}
- void avic_init_vmcb(struct vcpu_svm *svm)
+ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
{
- struct vmcb *vmcb = svm->vmcb;
struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm);
phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page));
phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page));
return 1;
}
+ unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu)
+ {
+ if (is_guest_mode(vcpu))
+ return APICV_INHIBIT_REASON_NESTED;
+ return 0;
+ }
+
static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat)
{
struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
BIT(APICV_INHIBIT_REASON_IRQWIN) |
BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
BIT(APICV_INHIBIT_REASON_X2APIC) |
- BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
+ BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
+ BIT(APICV_INHIBIT_REASON_SEV);
return supported & BIT(reason);
}
wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
}
+ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (static_cpu_has(X86_FEATURE_PKU) &&
- (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
- (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU)) &&
- vcpu->arch.pkru != vcpu->arch.host_pkru)
+ vcpu->arch.pkru != vcpu->arch.host_pkru &&
+ ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) ||
+ kvm_read_cr4_bits(vcpu, X86_CR4_PKE)))
write_pkru(vcpu->arch.pkru);
+ #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
}
EXPORT_SYMBOL_GPL(kvm_load_guest_xsave_state);
if (vcpu->arch.guest_state_protected)
return;
+ #ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
if (static_cpu_has(X86_FEATURE_PKU) &&
- (kvm_read_cr4_bits(vcpu, X86_CR4_PKE) ||
- (vcpu->arch.xcr0 & XFEATURE_MASK_PKRU))) {
+ ((vcpu->arch.xcr0 & XFEATURE_MASK_PKRU) ||
+ kvm_read_cr4_bits(vcpu, X86_CR4_PKE))) {
vcpu->arch.pkru = rdpkru();
if (vcpu->arch.pkru != vcpu->arch.host_pkru)
write_pkru(vcpu->arch.host_pkru);
}
+ #endif /* CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS */
if (kvm_read_cr4_bits(vcpu, X86_CR4_OSXSAVE)) {
* value, and that something deterministic happens if the guest
* invokes 64-bit SYSENTER.
*/
- data = get_canonical(data, vcpu_virt_addr_bits(vcpu));
+ data = __canonical_address(data, vcpu_virt_addr_bits(vcpu));
break;
case MSR_TSC_AUX:
if (!kvm_is_supported_user_return_msr(MSR_TSC_AUX))
kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
/* we verify if the enable bit is set... */
- vcpu->arch.pv_time_enabled = false;
- if (!(system_time & 1))
- return;
-
- if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
- &vcpu->arch.pv_time, system_time & ~1ULL,
- sizeof(struct pvclock_vcpu_time_info)))
- vcpu->arch.pv_time_enabled = true;
+ if (system_time & 1) {
+ kvm_gfn_to_pfn_cache_init(vcpu->kvm, &vcpu->arch.pv_time, vcpu,
+ KVM_HOST_USES_PFN, system_time & ~1ULL,
+ sizeof(struct pvclock_vcpu_time_info));
+ } else {
+ kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
+ }
return;
}
static void kvm_update_masterclock(struct kvm *kvm)
{
- kvm_hv_invalidate_tsc_page(kvm);
+ kvm_hv_request_tsc_page_update(kvm);
kvm_start_pvclock_update(kvm);
pvclock_update_vm_gtod_copy(kvm);
kvm_end_pvclock_update(kvm);
return data.clock;
}
- static void kvm_setup_pvclock_page(struct kvm_vcpu *v,
- struct gfn_to_hva_cache *cache,
- unsigned int offset)
+ static void kvm_setup_guest_pvclock(struct kvm_vcpu *v,
+ struct gfn_to_pfn_cache *gpc,
+ unsigned int offset)
{
struct kvm_vcpu_arch *vcpu = &v->arch;
- struct pvclock_vcpu_time_info guest_hv_clock;
+ struct pvclock_vcpu_time_info *guest_hv_clock;
+ unsigned long flags;
- if (unlikely(kvm_read_guest_offset_cached(v->kvm, cache,
- &guest_hv_clock, offset, sizeof(guest_hv_clock))))
- return;
+ read_lock_irqsave(&gpc->lock, flags);
+ while (!kvm_gfn_to_pfn_cache_check(v->kvm, gpc, gpc->gpa,
+ offset + sizeof(*guest_hv_clock))) {
+ read_unlock_irqrestore(&gpc->lock, flags);
+
+ if (kvm_gfn_to_pfn_cache_refresh(v->kvm, gpc, gpc->gpa,
+ offset + sizeof(*guest_hv_clock)))
+ return;
- /* This VCPU is paused, but it's legal for a guest to read another
+ read_lock_irqsave(&gpc->lock, flags);
+ }
+
+ guest_hv_clock = (void *)(gpc->khva + offset);
+
+ /*
+ * This VCPU is paused, but it's legal for a guest to read another
* VCPU's kvmclock, so we really have to follow the specification where
* it says that version is odd if data is being modified, and even after
* it is consistent.
- *
- * Version field updates must be kept separate. This is because
- * kvm_write_guest_cached might use a "rep movs" instruction, and
- * writes within a string instruction are weakly ordered. So there
- * are three writes overall.
- *
- * As a small optimization, only write the version field in the first
- * and third write. The vcpu->pv_time cache is still valid, because the
- * version field is the first in the struct.
*/
- 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_offset_cached(v->kvm, cache,
- &vcpu->hv_clock, offset,
- sizeof(vcpu->hv_clock.version));
+ guest_hv_clock->version = vcpu->hv_clock.version = (guest_hv_clock->version + 1) | 1;
smp_wmb();
/* retain PVCLOCK_GUEST_STOPPED if set in guest copy */
- vcpu->hv_clock.flags |= (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED);
+ vcpu->hv_clock.flags |= (guest_hv_clock->flags & PVCLOCK_GUEST_STOPPED);
if (vcpu->pvclock_set_guest_stopped_request) {
vcpu->hv_clock.flags |= PVCLOCK_GUEST_STOPPED;
vcpu->pvclock_set_guest_stopped_request = false;
}
- trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
+ memcpy(guest_hv_clock, &vcpu->hv_clock, sizeof(*guest_hv_clock));
+ smp_wmb();
- kvm_write_guest_offset_cached(v->kvm, cache,
- &vcpu->hv_clock, offset,
- sizeof(vcpu->hv_clock));
+ guest_hv_clock->version = ++vcpu->hv_clock.version;
- smp_wmb();
+ mark_page_dirty_in_slot(v->kvm, gpc->memslot, gpc->gpa >> PAGE_SHIFT);
+ read_unlock_irqrestore(&gpc->lock, flags);
- vcpu->hv_clock.version++;
- kvm_write_guest_offset_cached(v->kvm, cache,
- &vcpu->hv_clock, offset,
- sizeof(vcpu->hv_clock.version));
+ trace_kvm_pvclock_update(v->vcpu_id, &vcpu->hv_clock);
}
static int kvm_guest_time_update(struct kvm_vcpu *v)
vcpu->hv_clock.flags = pvclock_flags;
- if (vcpu->pv_time_enabled)
- kvm_setup_pvclock_page(v, &vcpu->pv_time, 0);
- if (vcpu->xen.vcpu_info_set)
- kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_info_cache,
- offsetof(struct compat_vcpu_info, time));
- if (vcpu->xen.vcpu_time_info_set)
- kvm_setup_pvclock_page(v, &vcpu->xen.vcpu_time_info_cache, 0);
+ if (vcpu->pv_time.active)
+ kvm_setup_guest_pvclock(v, &vcpu->pv_time, 0);
+ if (vcpu->xen.vcpu_info_cache.active)
+ kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_info_cache,
+ offsetof(struct compat_vcpu_info, time));
+ if (vcpu->xen.vcpu_time_info_cache.active)
+ kvm_setup_guest_pvclock(v, &vcpu->xen.vcpu_time_info_cache, 0);
- if (!v->vcpu_idx)
- kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
+ kvm_hv_setup_tsc_page(v->kvm, &vcpu->hv_clock);
return 0;
}
static void kvmclock_reset(struct kvm_vcpu *vcpu)
{
- vcpu->arch.pv_time_enabled = false;
+ kvm_gfn_to_pfn_cache_destroy(vcpu->kvm, &vcpu->arch.pv_time);
vcpu->arch.time = 0;
}
r = KVM_XEN_HVM_CONFIG_HYPERCALL_MSR |
KVM_XEN_HVM_CONFIG_INTERCEPT_HCALL |
KVM_XEN_HVM_CONFIG_SHARED_INFO |
- KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL;
+ KVM_XEN_HVM_CONFIG_EVTCHN_2LEVEL |
+ KVM_XEN_HVM_CONFIG_EVTCHN_SEND;
if (sched_info_on())
r |= KVM_XEN_HVM_CONFIG_RUNSTATE;
break;
r = boot_cpu_has(X86_FEATURE_XSAVE);
break;
case KVM_CAP_TSC_CONTROL:
+ case KVM_CAP_VM_TSC_CONTROL:
r = kvm_has_tsc_control;
break;
case KVM_CAP_X2APIC_API:
*/
static int kvm_set_guest_paused(struct kvm_vcpu *vcpu)
{
- if (!vcpu->arch.pv_time_enabled)
+ if (!vcpu->arch.pv_time.active)
return -EINVAL;
vcpu->arch.pvclock_set_guest_stopped_request = true;
kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
mutex_lock(&kvm->lock);
kvm_for_each_vcpu(i, vcpu, kvm) {
- if (!vcpu->arch.pv_time_enabled)
+ if (!vcpu->arch.pv_time.active)
continue;
ret = kvm_set_guest_paused(vcpu);
if (data.flags & ~KVM_CLOCK_VALID_FLAGS)
return -EINVAL;
- kvm_hv_invalidate_tsc_page(kvm);
+ kvm_hv_request_tsc_page_update(kvm);
kvm_start_pvclock_update(kvm);
pvclock_update_vm_gtod_copy(kvm);
r = kvm_xen_hvm_set_attr(kvm, &xha);
break;
}
+ case KVM_XEN_HVM_EVTCHN_SEND: {
+ struct kvm_irq_routing_xen_evtchn uxe;
+
+ r = -EFAULT;
+ if (copy_from_user(&uxe, argp, sizeof(uxe)))
+ goto out;
+ r = kvm_xen_hvm_evtchn_send(kvm, &uxe);
+ break;
+ }
#endif
case KVM_SET_CLOCK:
r = kvm_vm_ioctl_set_clock(kvm, argp);
case KVM_GET_CLOCK:
r = kvm_vm_ioctl_get_clock(kvm, argp);
break;
+ case KVM_SET_TSC_KHZ: {
+ u32 user_tsc_khz;
+
+ r = -EINVAL;
+ user_tsc_khz = (u32)arg;
+
+ if (kvm_has_tsc_control &&
+ user_tsc_khz >= kvm_max_guest_tsc_khz)
+ goto out;
+
+ if (user_tsc_khz == 0)
+ user_tsc_khz = tsc_khz;
+
+ WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz);
+ r = 0;
+
+ goto out;
+ }
+ case KVM_GET_TSC_KHZ: {
+ r = READ_ONCE(kvm->arch.default_tsc_khz);
+ goto out;
+ }
case KVM_MEMORY_ENCRYPT_OP: {
r = -ENOTTY;
if (!kvm_x86_ops.mem_enc_ioctl)
u32 dummy[2];
unsigned i;
- BUILD_BUG_ON_MSG(INTEL_PMC_MAX_FIXED != 4,
+ BUILD_BUG_ON_MSG(KVM_PMC_MAX_FIXED != 3,
"Please update the fixed PMCs in msrs_to_saved_all[]");
perf_get_x86_pmu_capability(&x86_pmu);
static void kvm_timer_init(void)
{
- max_tsc_khz = tsc_khz;
-
if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
- #ifdef CONFIG_CPU_FREQ
- struct cpufreq_policy *policy;
- int cpu;
-
- cpu = get_cpu();
- policy = cpufreq_cpu_get(cpu);
- if (policy) {
- if (policy->cpuinfo.max_freq)
- max_tsc_khz = policy->cpuinfo.max_freq;
- cpufreq_cpu_put(policy);
+ max_tsc_khz = tsc_khz;
+
+ if (IS_ENABLED(CONFIG_CPU_FREQ)) {
+ struct cpufreq_policy *policy;
+ int cpu;
+
+ cpu = get_cpu();
+ policy = cpufreq_cpu_get(cpu);
+ if (policy) {
+ if (policy->cpuinfo.max_freq)
+ max_tsc_khz = policy->cpuinfo.max_freq;
+ cpufreq_cpu_put(policy);
+ }
+ put_cpu();
}
- put_cpu();
- #endif
cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
CPUFREQ_TRANSITION_NOTIFIER);
}
}
kvm_nr_uret_msrs = 0;
- r = kvm_mmu_module_init();
+ r = kvm_mmu_vendor_module_init();
if (r)
goto out_free_percpu;
}
if (pi_inject_timer == -1)
- pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER);
+ pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER);
#ifdef CONFIG_X86_64
pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
cancel_work_sync(&pvclock_gtod_work);
#endif
kvm_x86_ops.hardware_enable = NULL;
- kvm_mmu_module_exit();
+ kvm_mmu_vendor_module_exit();
free_percpu(user_return_msrs);
kmem_cache_destroy(x86_emulator_cache);
#ifdef CONFIG_KVM_XEN
}
EXPORT_SYMBOL_GPL(kvm_apicv_activated);
+ bool kvm_vcpu_apicv_activated(struct kvm_vcpu *vcpu)
+ {
+ ulong vm_reasons = READ_ONCE(vcpu->kvm->arch.apicv_inhibit_reasons);
+ ulong vcpu_reasons = static_call(kvm_x86_vcpu_get_apicv_inhibit_reasons)(vcpu);
+
+ return (vm_reasons | vcpu_reasons) == 0;
+ }
+ EXPORT_SYMBOL_GPL(kvm_vcpu_apicv_activated);
static void set_or_clear_apicv_inhibit(unsigned long *inhibits,
enum kvm_apicv_inhibit reason, bool set)
char instruction[3];
unsigned long rip = kvm_rip_read(vcpu);
+ /*
+ * If the quirk is disabled, synthesize a #UD and let the guest pick up
+ * the pieces.
+ */
+ if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_FIX_HYPERCALL_INSN)) {
+ ctxt->exception.error_code_valid = false;
+ ctxt->exception.vector = UD_VECTOR;
+ ctxt->have_exception = true;
+ return X86EMUL_PROPAGATE_FAULT;
+ }
+
static_call(kvm_x86_patch_hypercall)(vcpu, instruction);
return emulator_write_emulated(ctxt, rip, instruction, 3,
down_read(&vcpu->kvm->arch.apicv_update_lock);
- activate = kvm_apicv_activated(vcpu->kvm);
+ activate = kvm_vcpu_apicv_activated(vcpu);
+
if (vcpu->arch.apicv_active == activate)
goto out;
* per-VM state, and responsing vCPUs must wait for the update
* to complete before servicing KVM_REQ_APICV_UPDATE.
*/
- WARN_ON_ONCE(kvm_apicv_activated(vcpu->kvm) != kvm_vcpu_apicv_active(vcpu));
+ WARN_ON_ONCE(kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu));
exit_fastpath = static_call(kvm_x86_vcpu_run)(vcpu);
if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
break;
kvm_clear_request(KVM_REQ_UNBLOCK, vcpu);
+ if (kvm_xen_has_pending_events(vcpu))
+ kvm_xen_inject_pending_events(vcpu);
+
if (kvm_cpu_has_pending_timer(vcpu))
kvm_inject_pending_timer_irqs(vcpu);
vcpu->arch.arch_capabilities = kvm_get_arch_capabilities();
vcpu->arch.msr_platform_info = MSR_PLATFORM_INFO_CPUID_FAULT;
+ kvm_xen_init_vcpu(vcpu);
kvm_vcpu_mtrr_init(vcpu);
vcpu_load(vcpu);
- kvm_set_tsc_khz(vcpu, max_tsc_khz);
+ kvm_set_tsc_khz(vcpu, vcpu->kvm->arch.default_tsc_khz);
kvm_vcpu_reset(vcpu, false);
kvm_init_mmu(vcpu);
vcpu_put(vcpu);
free_cpumask_var(vcpu->arch.wbinvd_dirty_mask);
fpu_free_guest_fpstate(&vcpu->arch.guest_fpu);
+ kvm_xen_destroy_vcpu(vcpu);
kvm_hv_vcpu_uninit(vcpu);
kvm_pmu_destroy(vcpu);
kfree(vcpu->arch.mce_banks);
pvclock_update_vm_gtod_copy(kvm);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+ kvm->arch.default_tsc_khz = max_tsc_khz ? : tsc_khz;
kvm->arch.guest_can_read_msr_platform_info = true;
kvm->arch.enable_pmu = enable_pmu;
kvm_x86_ops.nested_ops->hv_timer_pending(vcpu))
return true;
+ if (kvm_xen_has_pending_events(vcpu))
+ return true;
+
return false;
}
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_exit);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_enter);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
+
+static int __init kvm_x86_init(void)
+{
+ kvm_mmu_x86_module_init();
+ return 0;
+}
+module_init(kvm_x86_init);
+
+static void __exit kvm_x86_exit(void)
+{
+ /*
+ * If module_init() is implemented, module_exit() must also be
+ * implemented to allow module unload.
+ */
+}
+module_exit(kvm_x86_exit);
/aarch64/debug-exceptions
/aarch64/get-reg-list
/aarch64/psci_cpu_on_test
+/aarch64/vcpu_width_config
/aarch64/vgic_init
/aarch64/vgic_irq
/s390x/memop
/x86_64/debug_regs
/x86_64/evmcs_test
/x86_64/emulator_error_test
+ /x86_64/fix_hypercall_test
/x86_64/get_msr_index_features
/x86_64/kvm_clock_test
/x86_64/kvm_pv_test
/x86_64/hyperv_clock
/x86_64/hyperv_cpuid
/x86_64/hyperv_features
+/x86_64/hyperv_svm_test
/x86_64/mmio_warning_test
/x86_64/mmu_role_test
/x86_64/platform_info_test
/x86_64/state_test
/x86_64/svm_vmcall_test
/x86_64/svm_int_ctl_test
+/x86_64/tsc_scaling_sync
/x86_64/sync_regs_test
/x86_64/tsc_msrs_test
/x86_64/userspace_io_test
TEST_GEN_PROGS_x86_64 += x86_64/get_msr_index_features
TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
TEST_GEN_PROGS_x86_64 += x86_64/emulator_error_test
+ TEST_GEN_PROGS_x86_64 += x86_64/fix_hypercall_test
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_clock
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
TEST_GEN_PROGS_x86_64 += x86_64/hyperv_features
TEST_GEN_PROGS_x86_64 += x86_64/vmx_preemption_timer_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_vmcall_test
TEST_GEN_PROGS_x86_64 += x86_64/svm_int_ctl_test
+ TEST_GEN_PROGS_x86_64 += x86_64/tsc_scaling_sync
TEST_GEN_PROGS_x86_64 += x86_64/sync_regs_test
TEST_GEN_PROGS_x86_64 += x86_64/userspace_io_test
TEST_GEN_PROGS_x86_64 += x86_64/userspace_msr_exit_test
TEST_GEN_PROGS_aarch64 += aarch64/debug-exceptions
TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
TEST_GEN_PROGS_aarch64 += aarch64/psci_cpu_on_test
+TEST_GEN_PROGS_aarch64 += aarch64/vcpu_width_config
TEST_GEN_PROGS_aarch64 += aarch64/vgic_init
TEST_GEN_PROGS_aarch64 += aarch64/vgic_irq
TEST_GEN_PROGS_aarch64 += demand_paging_test
CFLAGS += -Wall -Wstrict-prototypes -Wuninitialized -O2 -g -std=gnu99 \
-fno-stack-protector -fno-PIE -I$(LINUX_TOOL_INCLUDE) \
-I$(LINUX_TOOL_ARCH_INCLUDE) -I$(LINUX_HDR_PATH) -Iinclude \
- -I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS)
+ -I$(<D) -Iinclude/$(UNAME_M) -I.. $(EXTRA_CFLAGS) $(KHDR_INCLUDES)
no-pie-option := $(call try-run, echo 'int main() { return 0; }' | \
$(CC) -Werror -no-pie -x c - -o "$$TMP", -no-pie)